linux/net/core/sock.c

3720 lines
89 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* INET An implementation of the TCP/IP protocol suite for the LINUX
* operating system. INET is implemented using the BSD Socket
* interface as the means of communication with the user level.
*
* Generic socket support routines. Memory allocators, socket lock/release
* handler for protocols to use and generic option handler.
*
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Florian La Roche, <flla@stud.uni-sb.de>
* Alan Cox, <A.Cox@swansea.ac.uk>
*
* Fixes:
* Alan Cox : Numerous verify_area() problems
* Alan Cox : Connecting on a connecting socket
* now returns an error for tcp.
* Alan Cox : sock->protocol is set correctly.
* and is not sometimes left as 0.
* Alan Cox : connect handles icmp errors on a
* connect properly. Unfortunately there
* is a restart syscall nasty there. I
* can't match BSD without hacking the C
* library. Ideas urgently sought!
* Alan Cox : Disallow bind() to addresses that are
* not ours - especially broadcast ones!!
* Alan Cox : Socket 1024 _IS_ ok for users. (fencepost)
* Alan Cox : sock_wfree/sock_rfree don't destroy sockets,
* instead they leave that for the DESTROY timer.
* Alan Cox : Clean up error flag in accept
* Alan Cox : TCP ack handling is buggy, the DESTROY timer
* was buggy. Put a remove_sock() in the handler
* for memory when we hit 0. Also altered the timer
* code. The ACK stuff can wait and needs major
* TCP layer surgery.
* Alan Cox : Fixed TCP ack bug, removed remove sock
* and fixed timer/inet_bh race.
* Alan Cox : Added zapped flag for TCP
* Alan Cox : Move kfree_skb into skbuff.c and tidied up surplus code
* Alan Cox : for new sk_buff allocations wmalloc/rmalloc now call alloc_skb
* Alan Cox : kfree_s calls now are kfree_skbmem so we can track skb resources
* Alan Cox : Supports socket option broadcast now as does udp. Packet and raw need fixing.
* Alan Cox : Added RCVBUF,SNDBUF size setting. It suddenly occurred to me how easy it was so...
* Rick Sladkey : Relaxed UDP rules for matching packets.
* C.E.Hawkins : IFF_PROMISC/SIOCGHWADDR support
* Pauline Middelink : identd support
* Alan Cox : Fixed connect() taking signals I think.
* Alan Cox : SO_LINGER supported
* Alan Cox : Error reporting fixes
* Anonymous : inet_create tidied up (sk->reuse setting)
* Alan Cox : inet sockets don't set sk->type!
* Alan Cox : Split socket option code
* Alan Cox : Callbacks
* Alan Cox : Nagle flag for Charles & Johannes stuff
* Alex : Removed restriction on inet fioctl
* Alan Cox : Splitting INET from NET core
* Alan Cox : Fixed bogus SO_TYPE handling in getsockopt()
* Adam Caldwell : Missing return in SO_DONTROUTE/SO_DEBUG code
* Alan Cox : Split IP from generic code
* Alan Cox : New kfree_skbmem()
* Alan Cox : Make SO_DEBUG superuser only.
* Alan Cox : Allow anyone to clear SO_DEBUG
* (compatibility fix)
* Alan Cox : Added optimistic memory grabbing for AF_UNIX throughput.
* Alan Cox : Allocator for a socket is settable.
* Alan Cox : SO_ERROR includes soft errors.
* Alan Cox : Allow NULL arguments on some SO_ opts
* Alan Cox : Generic socket allocation to make hooks
* easier (suggested by Craig Metz).
* Michael Pall : SO_ERROR returns positive errno again
* Steve Whitehouse: Added default destructor to free
* protocol private data.
* Steve Whitehouse: Added various other default routines
* common to several socket families.
* Chris Evans : Call suser() check last on F_SETOWN
* Jay Schulist : Added SO_ATTACH_FILTER and SO_DETACH_FILTER.
* Andi Kleen : Add sock_kmalloc()/sock_kfree_s()
* Andi Kleen : Fix write_space callback
* Chris Evans : Security fixes - signedness again
* Arnaldo C. Melo : cleanups, use skb_queue_purge
*
* To Fix:
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <asm/unaligned.h>
#include <linux/capability.h>
#include <linux/errno.h>
#include <linux/errqueue.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/in.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/sched.h>
#include <linux/sched/mm.h>
#include <linux/timer.h>
#include <linux/string.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/interrupt.h>
#include <linux/poll.h>
#include <linux/tcp.h>
#include <linux/init.h>
#include <linux/highmem.h>
#include <linux/user_namespace.h>
static keys: Introduce 'struct static_key', static_key_true()/false() and static_key_slow_[inc|dec]() So here's a boot tested patch on top of Jason's series that does all the cleanups I talked about and turns jump labels into a more intuitive to use facility. It should also address the various misconceptions and confusions that surround jump labels. Typical usage scenarios: #include <linux/static_key.h> struct static_key key = STATIC_KEY_INIT_TRUE; if (static_key_false(&key)) do unlikely code else do likely code Or: if (static_key_true(&key)) do likely code else do unlikely code The static key is modified via: static_key_slow_inc(&key); ... static_key_slow_dec(&key); The 'slow' prefix makes it abundantly clear that this is an expensive operation. I've updated all in-kernel code to use this everywhere. Note that I (intentionally) have not pushed through the rename blindly through to the lowest levels: the actual jump-label patching arch facility should be named like that, so we want to decouple jump labels from the static-key facility a bit. On non-jump-label enabled architectures static keys default to likely()/unlikely() branches. Signed-off-by: Ingo Molnar <mingo@elte.hu> Acked-by: Jason Baron <jbaron@redhat.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Cc: a.p.zijlstra@chello.nl Cc: mathieu.desnoyers@efficios.com Cc: davem@davemloft.net Cc: ddaney.cavm@gmail.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20120222085809.GA26397@elte.hu Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-24 07:31:31 +00:00
#include <linux/static_key.h>
#include <linux/memcontrol.h>
#include <linux/prefetch.h>
#include <linux/compat.h>
#include <linux/uaccess.h>
#include <linux/netdevice.h>
#include <net/protocol.h>
#include <linux/skbuff.h>
#include <net/net_namespace.h>
#include <net/request_sock.h>
#include <net/sock.h>
#include <linux/net_tstamp.h>
#include <net/xfrm.h>
#include <linux/ipsec.h>
cls_cgroup: Store classid in struct sock Up until now cls_cgroup has relied on fetching the classid out of the current executing thread. This runs into trouble when a packet processing is delayed in which case it may execute out of another thread's context. Furthermore, even when a packet is not delayed we may fail to classify it if soft IRQs have been disabled, because this scenario is indistinguishable from one where a packet unrelated to the current thread is processed by a real soft IRQ. In fact, the current semantics is inherently broken, as a single skb may be constructed out of the writes of two different tasks. A different manifestation of this problem is when the TCP stack transmits in response of an incoming ACK. This is currently unclassified. As we already have a concept of packet ownership for accounting purposes in the skb->sk pointer, this is a natural place to store the classid in a persistent manner. This patch adds the cls_cgroup classid in struct sock, filling up an existing hole on 64-bit :) The value is set at socket creation time. So all sockets created via socket(2) automatically gains the ID of the thread creating it. Whenever another process touches the socket by either reading or writing to it, we will change the socket classid to that of the process if it has a valid (non-zero) classid. For sockets created on inbound connections through accept(2), we inherit the classid of the original listening socket through sk_clone, possibly preceding the actual accept(2) call. In order to minimise risks, I have not made this the authoritative classid. For now it is only used as a backup when we execute with soft IRQs disabled. Once we're completely happy with its semantics we can use it as the sole classid. Footnote: I have rearranged the error path on cls_group module creation. If we didn't do this, then there is a window where someone could create a tc rule using cls_group before the cgroup subsystem has been registered. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-05-24 07:12:34 +00:00
#include <net/cls_cgroup.h>
#include <net/netprio_cgroup.h>
#include <linux/sock_diag.h>
#include <linux/filter.h>
#include <net/sock_reuseport.h>
bpf: Introduce bpf sk local storage After allowing a bpf prog to - directly read the skb->sk ptr - get the fullsock bpf_sock by "bpf_sk_fullsock()" - get the bpf_tcp_sock by "bpf_tcp_sock()" - get the listener sock by "bpf_get_listener_sock()" - avoid duplicating the fields of "(bpf_)sock" and "(bpf_)tcp_sock" into different bpf running context. this patch is another effort to make bpf's network programming more intuitive to do (together with memory and performance benefit). When bpf prog needs to store data for a sk, the current practice is to define a map with the usual 4-tuples (src/dst ip/port) as the key. If multiple bpf progs require to store different sk data, multiple maps have to be defined. Hence, wasting memory to store the duplicated keys (i.e. 4 tuples here) in each of the bpf map. [ The smallest key could be the sk pointer itself which requires some enhancement in the verifier and it is a separate topic. ] Also, the bpf prog needs to clean up the elem when sk is freed. Otherwise, the bpf map will become full and un-usable quickly. The sk-free tracking currently could be done during sk state transition (e.g. BPF_SOCK_OPS_STATE_CB). The size of the map needs to be predefined which then usually ended-up with an over-provisioned map in production. Even the map was re-sizable, while the sk naturally come and go away already, this potential re-size operation is arguably redundant if the data can be directly connected to the sk itself instead of proxy-ing through a bpf map. This patch introduces sk->sk_bpf_storage to provide local storage space at sk for bpf prog to use. The space will be allocated when the first bpf prog has created data for this particular sk. The design optimizes the bpf prog's lookup (and then optionally followed by an inline update). bpf_spin_lock should be used if the inline update needs to be protected. BPF_MAP_TYPE_SK_STORAGE: ----------------------- To define a bpf "sk-local-storage", a BPF_MAP_TYPE_SK_STORAGE map (new in this patch) needs to be created. Multiple BPF_MAP_TYPE_SK_STORAGE maps can be created to fit different bpf progs' needs. The map enforces BTF to allow printing the sk-local-storage during a system-wise sk dump (e.g. "ss -ta") in the future. The purpose of a BPF_MAP_TYPE_SK_STORAGE map is not for lookup/update/delete a "sk-local-storage" data from a particular sk. Think of the map as a meta-data (or "type") of a "sk-local-storage". This particular "type" of "sk-local-storage" data can then be stored in any sk. The main purposes of this map are mostly: 1. Define the size of a "sk-local-storage" type. 2. Provide a similar syscall userspace API as the map (e.g. lookup/update, map-id, map-btf...etc.) 3. Keep track of all sk's storages of this "type" and clean them up when the map is freed. sk->sk_bpf_storage: ------------------ The main lookup/update/delete is done on sk->sk_bpf_storage (which is a "struct bpf_sk_storage"). When doing a lookup, the "map" pointer is now used as the "key" to search on the sk_storage->list. The "map" pointer is actually serving as the "type" of the "sk-local-storage" that is being requested. To allow very fast lookup, it should be as fast as looking up an array at a stable-offset. At the same time, it is not ideal to set a hard limit on the number of sk-local-storage "type" that the system can have. Hence, this patch takes a cache approach. The last search result from sk_storage->list is cached in sk_storage->cache[] which is a stable sized array. Each "sk-local-storage" type has a stable offset to the cache[] array. In the future, a map's flag could be introduced to do cache opt-out/enforcement if it became necessary. The cache size is 16 (i.e. 16 types of "sk-local-storage"). Programs can share map. On the program side, having a few bpf_progs running in the networking hotpath is already a lot. The bpf_prog should have already consolidated the existing sock-key-ed map usage to minimize the map lookup penalty. 16 has enough runway to grow. All sk-local-storage data will be removed from sk->sk_bpf_storage during sk destruction. bpf_sk_storage_get() and bpf_sk_storage_delete(): ------------------------------------------------ Instead of using bpf_map_(lookup|update|delete)_elem(), the bpf prog needs to use the new helper bpf_sk_storage_get() and bpf_sk_storage_delete(). The verifier can then enforce the ARG_PTR_TO_SOCKET argument. The bpf_sk_storage_get() also allows to "create" new elem if one does not exist in the sk. It is done by the new BPF_SK_STORAGE_GET_F_CREATE flag. An optional value can also be provided as the initial value during BPF_SK_STORAGE_GET_F_CREATE. The BPF_MAP_TYPE_SK_STORAGE also supports bpf_spin_lock. Together, it has eliminated the potential use cases for an equivalent bpf_map_update_elem() API (for bpf_prog) in this patch. Misc notes: ---------- 1. map_get_next_key is not supported. From the userspace syscall perspective, the map has the socket fd as the key while the map can be shared by pinned-file or map-id. Since btf is enforced, the existing "ss" could be enhanced to pretty print the local-storage. Supporting a kernel defined btf with 4 tuples as the return key could be explored later also. 2. The sk->sk_lock cannot be acquired. Atomic operations is used instead. e.g. cmpxchg is done on the sk->sk_bpf_storage ptr. Please refer to the source code comments for the details in synchronization cases and considerations. 3. The mem is charged to the sk->sk_omem_alloc as the sk filter does. Benchmark: --------- Here is the benchmark data collected by turning on the "kernel.bpf_stats_enabled" sysctl. Two bpf progs are tested: One bpf prog with the usual bpf hashmap (max_entries = 8192) with the sk ptr as the key. (verifier is modified to support sk ptr as the key That should have shortened the key lookup time.) Another bpf prog is with the new BPF_MAP_TYPE_SK_STORAGE. Both are storing a "u32 cnt", do a lookup on "egress_skb/cgroup" for each egress skb and then bump the cnt. netperf is used to drive data with 4096 connected UDP sockets. BPF_MAP_TYPE_HASH with a modifier verifier (152ns per bpf run) 27: cgroup_skb name egress_sk_map tag 74f56e832918070b run_time_ns 58280107540 run_cnt 381347633 loaded_at 2019-04-15T13:46:39-0700 uid 0 xlated 344B jited 258B memlock 4096B map_ids 16 btf_id 5 BPF_MAP_TYPE_SK_STORAGE in this patch (66ns per bpf run) 30: cgroup_skb name egress_sk_stora tag d4aa70984cc7bbf6 run_time_ns 25617093319 run_cnt 390989739 loaded_at 2019-04-15T13:47:54-0700 uid 0 xlated 168B jited 156B memlock 4096B map_ids 17 btf_id 6 Here is a high-level picture on how are the objects organized: sk ┌──────┐ │ │ │ │ │ │ │*sk_bpf_storage─────▶ bpf_sk_storage └──────┘ ┌───────┐ ┌───────────┤ list │ │ │ │ │ │ │ │ │ │ │ └───────┘ │ │ elem │ ┌────────┐ ├─▶│ snode │ │ ├────────┤ │ │ data │ bpf_map │ ├────────┤ ┌─────────┐ │ │map_node│◀─┬─────┤ list │ │ └────────┘ │ │ │ │ │ │ │ │ elem │ │ │ │ ┌────────┐ │ └─────────┘ └─▶│ snode │ │ ├────────┤ │ bpf_map │ data │ │ ┌─────────┐ ├────────┤ │ │ list ├───────▶│map_node│ │ │ │ └────────┘ │ │ │ │ │ │ elem │ └─────────┘ ┌────────┐ │ ┌─▶│ snode │ │ │ ├────────┤ │ │ │ data │ │ │ ├────────┤ │ │ │map_node│◀─┘ │ └────────┘ │ │ │ ┌───────┐ sk └──────────│ list │ ┌──────┐ │ │ │ │ │ │ │ │ │ │ │ │ └───────┘ │*sk_bpf_storage───────▶bpf_sk_storage └──────┘ Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-04-26 23:39:39 +00:00
#include <net/bpf_sk_storage.h>
#include <trace/events/sock.h>
#include <net/tcp.h>
#include <net/busy_poll.h>
static DEFINE_MUTEX(proto_list_mutex);
static LIST_HEAD(proto_list);
static void sock_inuse_add(struct net *net, int val);
/**
* sk_ns_capable - General socket capability test
* @sk: Socket to use a capability on or through
* @user_ns: The user namespace of the capability to use
* @cap: The capability to use
*
* Test to see if the opener of the socket had when the socket was
* created and the current process has the capability @cap in the user
* namespace @user_ns.
*/
bool sk_ns_capable(const struct sock *sk,
struct user_namespace *user_ns, int cap)
{
return file_ns_capable(sk->sk_socket->file, user_ns, cap) &&
ns_capable(user_ns, cap);
}
EXPORT_SYMBOL(sk_ns_capable);
/**
* sk_capable - Socket global capability test
* @sk: Socket to use a capability on or through
* @cap: The global capability to use
*
* Test to see if the opener of the socket had when the socket was
* created and the current process has the capability @cap in all user
* namespaces.
*/
bool sk_capable(const struct sock *sk, int cap)
{
return sk_ns_capable(sk, &init_user_ns, cap);
}
EXPORT_SYMBOL(sk_capable);
/**
* sk_net_capable - Network namespace socket capability test
* @sk: Socket to use a capability on or through
* @cap: The capability to use
*
* Test to see if the opener of the socket had when the socket was created
* and the current process has the capability @cap over the network namespace
* the socket is a member of.
*/
bool sk_net_capable(const struct sock *sk, int cap)
{
return sk_ns_capable(sk, sock_net(sk)->user_ns, cap);
}
EXPORT_SYMBOL(sk_net_capable);
/*
* Each address family might have different locking rules, so we have
net: Work around lockdep limitation in sockets that use sockets Lockdep issues a circular dependency warning when AFS issues an operation through AF_RXRPC from a context in which the VFS/VM holds the mmap_sem. The theory lockdep comes up with is as follows: (1) If the pagefault handler decides it needs to read pages from AFS, it calls AFS with mmap_sem held and AFS begins an AF_RXRPC call, but creating a call requires the socket lock: mmap_sem must be taken before sk_lock-AF_RXRPC (2) afs_open_socket() opens an AF_RXRPC socket and binds it. rxrpc_bind() binds the underlying UDP socket whilst holding its socket lock. inet_bind() takes its own socket lock: sk_lock-AF_RXRPC must be taken before sk_lock-AF_INET (3) Reading from a TCP socket into a userspace buffer might cause a fault and thus cause the kernel to take the mmap_sem, but the TCP socket is locked whilst doing this: sk_lock-AF_INET must be taken before mmap_sem However, lockdep's theory is wrong in this instance because it deals only with lock classes and not individual locks. The AF_INET lock in (2) isn't really equivalent to the AF_INET lock in (3) as the former deals with a socket entirely internal to the kernel that never sees userspace. This is a limitation in the design of lockdep. Fix the general case by: (1) Double up all the locking keys used in sockets so that one set are used if the socket is created by userspace and the other set is used if the socket is created by the kernel. (2) Store the kern parameter passed to sk_alloc() in a variable in the sock struct (sk_kern_sock). This informs sock_lock_init(), sock_init_data() and sk_clone_lock() as to the lock keys to be used. Note that the child created by sk_clone_lock() inherits the parent's kern setting. (3) Add a 'kern' parameter to ->accept() that is analogous to the one passed in to ->create() that distinguishes whether kernel_accept() or sys_accept4() was the caller and can be passed to sk_alloc(). Note that a lot of accept functions merely dequeue an already allocated socket. I haven't touched these as the new socket already exists before we get the parameter. Note also that there are a couple of places where I've made the accepted socket unconditionally kernel-based: irda_accept() rds_rcp_accept_one() tcp_accept_from_sock() because they follow a sock_create_kern() and accept off of that. Whilst creating this, I noticed that lustre and ocfs don't create sockets through sock_create_kern() and thus they aren't marked as for-kernel, though they appear to be internal. I wonder if these should do that so that they use the new set of lock keys. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-09 08:09:05 +00:00
* one slock key per address family and separate keys for internal and
* userspace sockets.
*/
static struct lock_class_key af_family_keys[AF_MAX];
net: Work around lockdep limitation in sockets that use sockets Lockdep issues a circular dependency warning when AFS issues an operation through AF_RXRPC from a context in which the VFS/VM holds the mmap_sem. The theory lockdep comes up with is as follows: (1) If the pagefault handler decides it needs to read pages from AFS, it calls AFS with mmap_sem held and AFS begins an AF_RXRPC call, but creating a call requires the socket lock: mmap_sem must be taken before sk_lock-AF_RXRPC (2) afs_open_socket() opens an AF_RXRPC socket and binds it. rxrpc_bind() binds the underlying UDP socket whilst holding its socket lock. inet_bind() takes its own socket lock: sk_lock-AF_RXRPC must be taken before sk_lock-AF_INET (3) Reading from a TCP socket into a userspace buffer might cause a fault and thus cause the kernel to take the mmap_sem, but the TCP socket is locked whilst doing this: sk_lock-AF_INET must be taken before mmap_sem However, lockdep's theory is wrong in this instance because it deals only with lock classes and not individual locks. The AF_INET lock in (2) isn't really equivalent to the AF_INET lock in (3) as the former deals with a socket entirely internal to the kernel that never sees userspace. This is a limitation in the design of lockdep. Fix the general case by: (1) Double up all the locking keys used in sockets so that one set are used if the socket is created by userspace and the other set is used if the socket is created by the kernel. (2) Store the kern parameter passed to sk_alloc() in a variable in the sock struct (sk_kern_sock). This informs sock_lock_init(), sock_init_data() and sk_clone_lock() as to the lock keys to be used. Note that the child created by sk_clone_lock() inherits the parent's kern setting. (3) Add a 'kern' parameter to ->accept() that is analogous to the one passed in to ->create() that distinguishes whether kernel_accept() or sys_accept4() was the caller and can be passed to sk_alloc(). Note that a lot of accept functions merely dequeue an already allocated socket. I haven't touched these as the new socket already exists before we get the parameter. Note also that there are a couple of places where I've made the accepted socket unconditionally kernel-based: irda_accept() rds_rcp_accept_one() tcp_accept_from_sock() because they follow a sock_create_kern() and accept off of that. Whilst creating this, I noticed that lustre and ocfs don't create sockets through sock_create_kern() and thus they aren't marked as for-kernel, though they appear to be internal. I wonder if these should do that so that they use the new set of lock keys. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-09 08:09:05 +00:00
static struct lock_class_key af_family_kern_keys[AF_MAX];
static struct lock_class_key af_family_slock_keys[AF_MAX];
net: Work around lockdep limitation in sockets that use sockets Lockdep issues a circular dependency warning when AFS issues an operation through AF_RXRPC from a context in which the VFS/VM holds the mmap_sem. The theory lockdep comes up with is as follows: (1) If the pagefault handler decides it needs to read pages from AFS, it calls AFS with mmap_sem held and AFS begins an AF_RXRPC call, but creating a call requires the socket lock: mmap_sem must be taken before sk_lock-AF_RXRPC (2) afs_open_socket() opens an AF_RXRPC socket and binds it. rxrpc_bind() binds the underlying UDP socket whilst holding its socket lock. inet_bind() takes its own socket lock: sk_lock-AF_RXRPC must be taken before sk_lock-AF_INET (3) Reading from a TCP socket into a userspace buffer might cause a fault and thus cause the kernel to take the mmap_sem, but the TCP socket is locked whilst doing this: sk_lock-AF_INET must be taken before mmap_sem However, lockdep's theory is wrong in this instance because it deals only with lock classes and not individual locks. The AF_INET lock in (2) isn't really equivalent to the AF_INET lock in (3) as the former deals with a socket entirely internal to the kernel that never sees userspace. This is a limitation in the design of lockdep. Fix the general case by: (1) Double up all the locking keys used in sockets so that one set are used if the socket is created by userspace and the other set is used if the socket is created by the kernel. (2) Store the kern parameter passed to sk_alloc() in a variable in the sock struct (sk_kern_sock). This informs sock_lock_init(), sock_init_data() and sk_clone_lock() as to the lock keys to be used. Note that the child created by sk_clone_lock() inherits the parent's kern setting. (3) Add a 'kern' parameter to ->accept() that is analogous to the one passed in to ->create() that distinguishes whether kernel_accept() or sys_accept4() was the caller and can be passed to sk_alloc(). Note that a lot of accept functions merely dequeue an already allocated socket. I haven't touched these as the new socket already exists before we get the parameter. Note also that there are a couple of places where I've made the accepted socket unconditionally kernel-based: irda_accept() rds_rcp_accept_one() tcp_accept_from_sock() because they follow a sock_create_kern() and accept off of that. Whilst creating this, I noticed that lustre and ocfs don't create sockets through sock_create_kern() and thus they aren't marked as for-kernel, though they appear to be internal. I wonder if these should do that so that they use the new set of lock keys. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-09 08:09:05 +00:00
static struct lock_class_key af_family_kern_slock_keys[AF_MAX];
/*
* Make lock validator output more readable. (we pre-construct these
* strings build-time, so that runtime initialization of socket
* locks is fast):
*/
net: Work around lockdep limitation in sockets that use sockets Lockdep issues a circular dependency warning when AFS issues an operation through AF_RXRPC from a context in which the VFS/VM holds the mmap_sem. The theory lockdep comes up with is as follows: (1) If the pagefault handler decides it needs to read pages from AFS, it calls AFS with mmap_sem held and AFS begins an AF_RXRPC call, but creating a call requires the socket lock: mmap_sem must be taken before sk_lock-AF_RXRPC (2) afs_open_socket() opens an AF_RXRPC socket and binds it. rxrpc_bind() binds the underlying UDP socket whilst holding its socket lock. inet_bind() takes its own socket lock: sk_lock-AF_RXRPC must be taken before sk_lock-AF_INET (3) Reading from a TCP socket into a userspace buffer might cause a fault and thus cause the kernel to take the mmap_sem, but the TCP socket is locked whilst doing this: sk_lock-AF_INET must be taken before mmap_sem However, lockdep's theory is wrong in this instance because it deals only with lock classes and not individual locks. The AF_INET lock in (2) isn't really equivalent to the AF_INET lock in (3) as the former deals with a socket entirely internal to the kernel that never sees userspace. This is a limitation in the design of lockdep. Fix the general case by: (1) Double up all the locking keys used in sockets so that one set are used if the socket is created by userspace and the other set is used if the socket is created by the kernel. (2) Store the kern parameter passed to sk_alloc() in a variable in the sock struct (sk_kern_sock). This informs sock_lock_init(), sock_init_data() and sk_clone_lock() as to the lock keys to be used. Note that the child created by sk_clone_lock() inherits the parent's kern setting. (3) Add a 'kern' parameter to ->accept() that is analogous to the one passed in to ->create() that distinguishes whether kernel_accept() or sys_accept4() was the caller and can be passed to sk_alloc(). Note that a lot of accept functions merely dequeue an already allocated socket. I haven't touched these as the new socket already exists before we get the parameter. Note also that there are a couple of places where I've made the accepted socket unconditionally kernel-based: irda_accept() rds_rcp_accept_one() tcp_accept_from_sock() because they follow a sock_create_kern() and accept off of that. Whilst creating this, I noticed that lustre and ocfs don't create sockets through sock_create_kern() and thus they aren't marked as for-kernel, though they appear to be internal. I wonder if these should do that so that they use the new set of lock keys. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-09 08:09:05 +00:00
#define _sock_locks(x) \
x "AF_UNSPEC", x "AF_UNIX" , x "AF_INET" , \
x "AF_AX25" , x "AF_IPX" , x "AF_APPLETALK", \
x "AF_NETROM", x "AF_BRIDGE" , x "AF_ATMPVC" , \
x "AF_X25" , x "AF_INET6" , x "AF_ROSE" , \
x "AF_DECnet", x "AF_NETBEUI" , x "AF_SECURITY" , \
x "AF_KEY" , x "AF_NETLINK" , x "AF_PACKET" , \
x "AF_ASH" , x "AF_ECONET" , x "AF_ATMSVC" , \
x "AF_RDS" , x "AF_SNA" , x "AF_IRDA" , \
x "AF_PPPOX" , x "AF_WANPIPE" , x "AF_LLC" , \
x "27" , x "28" , x "AF_CAN" , \
x "AF_TIPC" , x "AF_BLUETOOTH", x "IUCV" , \
x "AF_RXRPC" , x "AF_ISDN" , x "AF_PHONET" , \
x "AF_IEEE802154", x "AF_CAIF" , x "AF_ALG" , \
x "AF_NFC" , x "AF_VSOCK" , x "AF_KCM" , \
x "AF_QIPCRTR", x "AF_SMC" , x "AF_XDP" , \
x "AF_MAX"
net: Work around lockdep limitation in sockets that use sockets Lockdep issues a circular dependency warning when AFS issues an operation through AF_RXRPC from a context in which the VFS/VM holds the mmap_sem. The theory lockdep comes up with is as follows: (1) If the pagefault handler decides it needs to read pages from AFS, it calls AFS with mmap_sem held and AFS begins an AF_RXRPC call, but creating a call requires the socket lock: mmap_sem must be taken before sk_lock-AF_RXRPC (2) afs_open_socket() opens an AF_RXRPC socket and binds it. rxrpc_bind() binds the underlying UDP socket whilst holding its socket lock. inet_bind() takes its own socket lock: sk_lock-AF_RXRPC must be taken before sk_lock-AF_INET (3) Reading from a TCP socket into a userspace buffer might cause a fault and thus cause the kernel to take the mmap_sem, but the TCP socket is locked whilst doing this: sk_lock-AF_INET must be taken before mmap_sem However, lockdep's theory is wrong in this instance because it deals only with lock classes and not individual locks. The AF_INET lock in (2) isn't really equivalent to the AF_INET lock in (3) as the former deals with a socket entirely internal to the kernel that never sees userspace. This is a limitation in the design of lockdep. Fix the general case by: (1) Double up all the locking keys used in sockets so that one set are used if the socket is created by userspace and the other set is used if the socket is created by the kernel. (2) Store the kern parameter passed to sk_alloc() in a variable in the sock struct (sk_kern_sock). This informs sock_lock_init(), sock_init_data() and sk_clone_lock() as to the lock keys to be used. Note that the child created by sk_clone_lock() inherits the parent's kern setting. (3) Add a 'kern' parameter to ->accept() that is analogous to the one passed in to ->create() that distinguishes whether kernel_accept() or sys_accept4() was the caller and can be passed to sk_alloc(). Note that a lot of accept functions merely dequeue an already allocated socket. I haven't touched these as the new socket already exists before we get the parameter. Note also that there are a couple of places where I've made the accepted socket unconditionally kernel-based: irda_accept() rds_rcp_accept_one() tcp_accept_from_sock() because they follow a sock_create_kern() and accept off of that. Whilst creating this, I noticed that lustre and ocfs don't create sockets through sock_create_kern() and thus they aren't marked as for-kernel, though they appear to be internal. I wonder if these should do that so that they use the new set of lock keys. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-09 08:09:05 +00:00
static const char *const af_family_key_strings[AF_MAX+1] = {
net: Work around lockdep limitation in sockets that use sockets Lockdep issues a circular dependency warning when AFS issues an operation through AF_RXRPC from a context in which the VFS/VM holds the mmap_sem. The theory lockdep comes up with is as follows: (1) If the pagefault handler decides it needs to read pages from AFS, it calls AFS with mmap_sem held and AFS begins an AF_RXRPC call, but creating a call requires the socket lock: mmap_sem must be taken before sk_lock-AF_RXRPC (2) afs_open_socket() opens an AF_RXRPC socket and binds it. rxrpc_bind() binds the underlying UDP socket whilst holding its socket lock. inet_bind() takes its own socket lock: sk_lock-AF_RXRPC must be taken before sk_lock-AF_INET (3) Reading from a TCP socket into a userspace buffer might cause a fault and thus cause the kernel to take the mmap_sem, but the TCP socket is locked whilst doing this: sk_lock-AF_INET must be taken before mmap_sem However, lockdep's theory is wrong in this instance because it deals only with lock classes and not individual locks. The AF_INET lock in (2) isn't really equivalent to the AF_INET lock in (3) as the former deals with a socket entirely internal to the kernel that never sees userspace. This is a limitation in the design of lockdep. Fix the general case by: (1) Double up all the locking keys used in sockets so that one set are used if the socket is created by userspace and the other set is used if the socket is created by the kernel. (2) Store the kern parameter passed to sk_alloc() in a variable in the sock struct (sk_kern_sock). This informs sock_lock_init(), sock_init_data() and sk_clone_lock() as to the lock keys to be used. Note that the child created by sk_clone_lock() inherits the parent's kern setting. (3) Add a 'kern' parameter to ->accept() that is analogous to the one passed in to ->create() that distinguishes whether kernel_accept() or sys_accept4() was the caller and can be passed to sk_alloc(). Note that a lot of accept functions merely dequeue an already allocated socket. I haven't touched these as the new socket already exists before we get the parameter. Note also that there are a couple of places where I've made the accepted socket unconditionally kernel-based: irda_accept() rds_rcp_accept_one() tcp_accept_from_sock() because they follow a sock_create_kern() and accept off of that. Whilst creating this, I noticed that lustre and ocfs don't create sockets through sock_create_kern() and thus they aren't marked as for-kernel, though they appear to be internal. I wonder if these should do that so that they use the new set of lock keys. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-09 08:09:05 +00:00
_sock_locks("sk_lock-")
};
static const char *const af_family_slock_key_strings[AF_MAX+1] = {
net: Work around lockdep limitation in sockets that use sockets Lockdep issues a circular dependency warning when AFS issues an operation through AF_RXRPC from a context in which the VFS/VM holds the mmap_sem. The theory lockdep comes up with is as follows: (1) If the pagefault handler decides it needs to read pages from AFS, it calls AFS with mmap_sem held and AFS begins an AF_RXRPC call, but creating a call requires the socket lock: mmap_sem must be taken before sk_lock-AF_RXRPC (2) afs_open_socket() opens an AF_RXRPC socket and binds it. rxrpc_bind() binds the underlying UDP socket whilst holding its socket lock. inet_bind() takes its own socket lock: sk_lock-AF_RXRPC must be taken before sk_lock-AF_INET (3) Reading from a TCP socket into a userspace buffer might cause a fault and thus cause the kernel to take the mmap_sem, but the TCP socket is locked whilst doing this: sk_lock-AF_INET must be taken before mmap_sem However, lockdep's theory is wrong in this instance because it deals only with lock classes and not individual locks. The AF_INET lock in (2) isn't really equivalent to the AF_INET lock in (3) as the former deals with a socket entirely internal to the kernel that never sees userspace. This is a limitation in the design of lockdep. Fix the general case by: (1) Double up all the locking keys used in sockets so that one set are used if the socket is created by userspace and the other set is used if the socket is created by the kernel. (2) Store the kern parameter passed to sk_alloc() in a variable in the sock struct (sk_kern_sock). This informs sock_lock_init(), sock_init_data() and sk_clone_lock() as to the lock keys to be used. Note that the child created by sk_clone_lock() inherits the parent's kern setting. (3) Add a 'kern' parameter to ->accept() that is analogous to the one passed in to ->create() that distinguishes whether kernel_accept() or sys_accept4() was the caller and can be passed to sk_alloc(). Note that a lot of accept functions merely dequeue an already allocated socket. I haven't touched these as the new socket already exists before we get the parameter. Note also that there are a couple of places where I've made the accepted socket unconditionally kernel-based: irda_accept() rds_rcp_accept_one() tcp_accept_from_sock() because they follow a sock_create_kern() and accept off of that. Whilst creating this, I noticed that lustre and ocfs don't create sockets through sock_create_kern() and thus they aren't marked as for-kernel, though they appear to be internal. I wonder if these should do that so that they use the new set of lock keys. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-09 08:09:05 +00:00
_sock_locks("slock-")
};
static const char *const af_family_clock_key_strings[AF_MAX+1] = {
net: Work around lockdep limitation in sockets that use sockets Lockdep issues a circular dependency warning when AFS issues an operation through AF_RXRPC from a context in which the VFS/VM holds the mmap_sem. The theory lockdep comes up with is as follows: (1) If the pagefault handler decides it needs to read pages from AFS, it calls AFS with mmap_sem held and AFS begins an AF_RXRPC call, but creating a call requires the socket lock: mmap_sem must be taken before sk_lock-AF_RXRPC (2) afs_open_socket() opens an AF_RXRPC socket and binds it. rxrpc_bind() binds the underlying UDP socket whilst holding its socket lock. inet_bind() takes its own socket lock: sk_lock-AF_RXRPC must be taken before sk_lock-AF_INET (3) Reading from a TCP socket into a userspace buffer might cause a fault and thus cause the kernel to take the mmap_sem, but the TCP socket is locked whilst doing this: sk_lock-AF_INET must be taken before mmap_sem However, lockdep's theory is wrong in this instance because it deals only with lock classes and not individual locks. The AF_INET lock in (2) isn't really equivalent to the AF_INET lock in (3) as the former deals with a socket entirely internal to the kernel that never sees userspace. This is a limitation in the design of lockdep. Fix the general case by: (1) Double up all the locking keys used in sockets so that one set are used if the socket is created by userspace and the other set is used if the socket is created by the kernel. (2) Store the kern parameter passed to sk_alloc() in a variable in the sock struct (sk_kern_sock). This informs sock_lock_init(), sock_init_data() and sk_clone_lock() as to the lock keys to be used. Note that the child created by sk_clone_lock() inherits the parent's kern setting. (3) Add a 'kern' parameter to ->accept() that is analogous to the one passed in to ->create() that distinguishes whether kernel_accept() or sys_accept4() was the caller and can be passed to sk_alloc(). Note that a lot of accept functions merely dequeue an already allocated socket. I haven't touched these as the new socket already exists before we get the parameter. Note also that there are a couple of places where I've made the accepted socket unconditionally kernel-based: irda_accept() rds_rcp_accept_one() tcp_accept_from_sock() because they follow a sock_create_kern() and accept off of that. Whilst creating this, I noticed that lustre and ocfs don't create sockets through sock_create_kern() and thus they aren't marked as for-kernel, though they appear to be internal. I wonder if these should do that so that they use the new set of lock keys. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-09 08:09:05 +00:00
_sock_locks("clock-")
};
static const char *const af_family_kern_key_strings[AF_MAX+1] = {
_sock_locks("k-sk_lock-")
};
static const char *const af_family_kern_slock_key_strings[AF_MAX+1] = {
_sock_locks("k-slock-")
};
static const char *const af_family_kern_clock_key_strings[AF_MAX+1] = {
_sock_locks("k-clock-")
};
static const char *const af_family_rlock_key_strings[AF_MAX+1] = {
_sock_locks("rlock-")
};
static const char *const af_family_wlock_key_strings[AF_MAX+1] = {
_sock_locks("wlock-")
};
static const char *const af_family_elock_key_strings[AF_MAX+1] = {
_sock_locks("elock-")
};
/*
* sk_callback_lock and sk queues locking rules are per-address-family,
* so split the lock classes by using a per-AF key:
*/
static struct lock_class_key af_callback_keys[AF_MAX];
static struct lock_class_key af_rlock_keys[AF_MAX];
static struct lock_class_key af_wlock_keys[AF_MAX];
static struct lock_class_key af_elock_keys[AF_MAX];
net: Work around lockdep limitation in sockets that use sockets Lockdep issues a circular dependency warning when AFS issues an operation through AF_RXRPC from a context in which the VFS/VM holds the mmap_sem. The theory lockdep comes up with is as follows: (1) If the pagefault handler decides it needs to read pages from AFS, it calls AFS with mmap_sem held and AFS begins an AF_RXRPC call, but creating a call requires the socket lock: mmap_sem must be taken before sk_lock-AF_RXRPC (2) afs_open_socket() opens an AF_RXRPC socket and binds it. rxrpc_bind() binds the underlying UDP socket whilst holding its socket lock. inet_bind() takes its own socket lock: sk_lock-AF_RXRPC must be taken before sk_lock-AF_INET (3) Reading from a TCP socket into a userspace buffer might cause a fault and thus cause the kernel to take the mmap_sem, but the TCP socket is locked whilst doing this: sk_lock-AF_INET must be taken before mmap_sem However, lockdep's theory is wrong in this instance because it deals only with lock classes and not individual locks. The AF_INET lock in (2) isn't really equivalent to the AF_INET lock in (3) as the former deals with a socket entirely internal to the kernel that never sees userspace. This is a limitation in the design of lockdep. Fix the general case by: (1) Double up all the locking keys used in sockets so that one set are used if the socket is created by userspace and the other set is used if the socket is created by the kernel. (2) Store the kern parameter passed to sk_alloc() in a variable in the sock struct (sk_kern_sock). This informs sock_lock_init(), sock_init_data() and sk_clone_lock() as to the lock keys to be used. Note that the child created by sk_clone_lock() inherits the parent's kern setting. (3) Add a 'kern' parameter to ->accept() that is analogous to the one passed in to ->create() that distinguishes whether kernel_accept() or sys_accept4() was the caller and can be passed to sk_alloc(). Note that a lot of accept functions merely dequeue an already allocated socket. I haven't touched these as the new socket already exists before we get the parameter. Note also that there are a couple of places where I've made the accepted socket unconditionally kernel-based: irda_accept() rds_rcp_accept_one() tcp_accept_from_sock() because they follow a sock_create_kern() and accept off of that. Whilst creating this, I noticed that lustre and ocfs don't create sockets through sock_create_kern() and thus they aren't marked as for-kernel, though they appear to be internal. I wonder if these should do that so that they use the new set of lock keys. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-09 08:09:05 +00:00
static struct lock_class_key af_kern_callback_keys[AF_MAX];
/* Run time adjustable parameters. */
__u32 sysctl_wmem_max __read_mostly = SK_WMEM_MAX;
EXPORT_SYMBOL(sysctl_wmem_max);
__u32 sysctl_rmem_max __read_mostly = SK_RMEM_MAX;
EXPORT_SYMBOL(sysctl_rmem_max);
__u32 sysctl_wmem_default __read_mostly = SK_WMEM_MAX;
__u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX;
/* Maximal space eaten by iovec or ancillary data plus some space */
int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512);
EXPORT_SYMBOL(sysctl_optmem_max);
int sysctl_tstamp_allow_data __read_mostly = 1;
DEFINE_STATIC_KEY_FALSE(memalloc_socks_key);
EXPORT_SYMBOL_GPL(memalloc_socks_key);
/**
* sk_set_memalloc - sets %SOCK_MEMALLOC
* @sk: socket to set it on
*
* Set %SOCK_MEMALLOC on a socket for access to emergency reserves.
* It's the responsibility of the admin to adjust min_free_kbytes
* to meet the requirements
*/
void sk_set_memalloc(struct sock *sk)
{
sock_set_flag(sk, SOCK_MEMALLOC);
sk->sk_allocation |= __GFP_MEMALLOC;
static_branch_inc(&memalloc_socks_key);
}
EXPORT_SYMBOL_GPL(sk_set_memalloc);
void sk_clear_memalloc(struct sock *sk)
{
sock_reset_flag(sk, SOCK_MEMALLOC);
sk->sk_allocation &= ~__GFP_MEMALLOC;
static_branch_dec(&memalloc_socks_key);
netvm: prevent a stream-specific deadlock This patch series is based on top of "Swap-over-NBD without deadlocking v15" as it depends on the same reservation of PF_MEMALLOC reserves logic. When a user or administrator requires swap for their application, they create a swap partition and file, format it with mkswap and activate it with swapon. In diskless systems this is not an option so if swap if required then swapping over the network is considered. The two likely scenarios are when blade servers are used as part of a cluster where the form factor or maintenance costs do not allow the use of disks and thin clients. The Linux Terminal Server Project recommends the use of the Network Block Device (NBD) for swap but this is not always an option. There is no guarantee that the network attached storage (NAS) device is running Linux or supports NBD. However, it is likely that it supports NFS so there are users that want support for swapping over NFS despite any performance concern. Some distributions currently carry patches that support swapping over NFS but it would be preferable to support it in the mainline kernel. Patch 1 avoids a stream-specific deadlock that potentially affects TCP. Patch 2 is a small modification to SELinux to avoid using PFMEMALLOC reserves. Patch 3 adds three helpers for filesystems to handle swap cache pages. For example, page_file_mapping() returns page->mapping for file-backed pages and the address_space of the underlying swap file for swap cache pages. Patch 4 adds two address_space_operations to allow a filesystem to pin all metadata relevant to a swapfile in memory. Upon successful activation, the swapfile is marked SWP_FILE and the address space operation ->direct_IO is used for writing and ->readpage for reading in swap pages. Patch 5 notes that patch 3 is bolting filesystem-specific-swapfile-support onto the side and that the default handlers have different information to what is available to the filesystem. This patch refactors the code so that there are generic handlers for each of the new address_space operations. Patch 6 adds an API to allow a vector of kernel addresses to be translated to struct pages and pinned for IO. Patch 7 adds support for using highmem pages for swap by kmapping the pages before calling the direct_IO handler. Patch 8 updates NFS to use the helpers from patch 3 where necessary. Patch 9 avoids setting PF_private on PG_swapcache pages within NFS. Patch 10 implements the new swapfile-related address_space operations for NFS and teaches the direct IO handler how to manage kernel addresses. Patch 11 prevents page allocator recursions in NFS by using GFP_NOIO where appropriate. Patch 12 fixes a NULL pointer dereference that occurs when using swap-over-NFS. With the patches applied, it is possible to mount a swapfile that is on an NFS filesystem. Swap performance is not great with a swap stress test taking roughly twice as long to complete than if the swap device was backed by NBD. This patch: netvm: prevent a stream-specific deadlock It could happen that all !SOCK_MEMALLOC sockets have buffered so much data that we're over the global rmem limit. This will prevent SOCK_MEMALLOC buffers from receiving data, which will prevent userspace from running, which is needed to reduce the buffered data. Fix this by exempting the SOCK_MEMALLOC sockets from the rmem limit. Once this change it applied, it is important that sockets that set SOCK_MEMALLOC do not clear the flag until the socket is being torn down. If this happens, a warning is generated and the tokens reclaimed to avoid accounting errors until the bug is fixed. [davem@davemloft.net: Warning about clearing SOCK_MEMALLOC] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Mel Gorman <mgorman@suse.de> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Rik van Riel <riel@redhat.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Cc: Neil Brown <neilb@suse.de> Cc: Christoph Hellwig <hch@infradead.org> Cc: Mike Christie <michaelc@cs.wisc.edu> Cc: Eric B Munson <emunson@mgebm.net> Cc: Sebastian Andrzej Siewior <sebastian@breakpoint.cc> Cc: Mel Gorman <mgorman@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-07-31 23:44:41 +00:00
/*
* SOCK_MEMALLOC is allowed to ignore rmem limits to ensure forward
net, swap: Remove a warning and clarify why sk_mem_reclaim is required when deactivating swap Jeff Layton reported the following; [ 74.232485] ------------[ cut here ]------------ [ 74.233354] WARNING: CPU: 2 PID: 754 at net/core/sock.c:364 sk_clear_memalloc+0x51/0x80() [ 74.234790] Modules linked in: cts rpcsec_gss_krb5 nfsv4 dns_resolver nfs fscache xfs libcrc32c snd_hda_codec_generic snd_hda_intel snd_hda_controller snd_hda_codec snd_hda_core snd_hwdep snd_seq snd_seq_device nfsd snd_pcm snd_timer snd e1000 ppdev parport_pc joydev parport pvpanic soundcore floppy serio_raw i2c_piix4 pcspkr nfs_acl lockd virtio_balloon acpi_cpufreq auth_rpcgss grace sunrpc qxl drm_kms_helper ttm drm virtio_console virtio_blk virtio_pci ata_generic virtio_ring pata_acpi virtio [ 74.243599] CPU: 2 PID: 754 Comm: swapoff Not tainted 4.1.0-rc6+ #5 [ 74.244635] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 [ 74.245546] 0000000000000000 0000000079e69e31 ffff8800d066bde8 ffffffff8179263d [ 74.246786] 0000000000000000 0000000000000000 ffff8800d066be28 ffffffff8109e6fa [ 74.248175] 0000000000000000 ffff880118d48000 ffff8800d58f5c08 ffff880036e380a8 [ 74.249483] Call Trace: [ 74.249872] [<ffffffff8179263d>] dump_stack+0x45/0x57 [ 74.250703] [<ffffffff8109e6fa>] warn_slowpath_common+0x8a/0xc0 [ 74.251655] [<ffffffff8109e82a>] warn_slowpath_null+0x1a/0x20 [ 74.252585] [<ffffffff81661241>] sk_clear_memalloc+0x51/0x80 [ 74.253519] [<ffffffffa0116c72>] xs_disable_swap+0x42/0x80 [sunrpc] [ 74.254537] [<ffffffffa01109de>] rpc_clnt_swap_deactivate+0x7e/0xc0 [sunrpc] [ 74.255610] [<ffffffffa03e4fd7>] nfs_swap_deactivate+0x27/0x30 [nfs] [ 74.256582] [<ffffffff811e99d4>] destroy_swap_extents+0x74/0x80 [ 74.257496] [<ffffffff811ecb52>] SyS_swapoff+0x222/0x5c0 [ 74.258318] [<ffffffff81023f27>] ? syscall_trace_leave+0xc7/0x140 [ 74.259253] [<ffffffff81798dae>] system_call_fastpath+0x12/0x71 [ 74.260158] ---[ end trace 2530722966429f10 ]--- The warning in question was unnecessary but with Jeff's series the rules are also clearer. This patch removes the warning and updates the comment to explain why sk_mem_reclaim() may still be called. [jlayton: remove if (sk->sk_forward_alloc) conditional. As Leon points out that it's not needed.] Cc: Leon Romanovsky <leon@leon.nu> Signed-off-by: Mel Gorman <mgorman@suse.de> Signed-off-by: Jeff Layton <jeff.layton@primarydata.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-06-11 01:02:04 +00:00
* progress of swapping. SOCK_MEMALLOC may be cleared while
* it has rmem allocations due to the last swapfile being deactivated
* but there is a risk that the socket is unusable due to exceeding
* the rmem limits. Reclaim the reserves and obey rmem limits again.
netvm: prevent a stream-specific deadlock This patch series is based on top of "Swap-over-NBD without deadlocking v15" as it depends on the same reservation of PF_MEMALLOC reserves logic. When a user or administrator requires swap for their application, they create a swap partition and file, format it with mkswap and activate it with swapon. In diskless systems this is not an option so if swap if required then swapping over the network is considered. The two likely scenarios are when blade servers are used as part of a cluster where the form factor or maintenance costs do not allow the use of disks and thin clients. The Linux Terminal Server Project recommends the use of the Network Block Device (NBD) for swap but this is not always an option. There is no guarantee that the network attached storage (NAS) device is running Linux or supports NBD. However, it is likely that it supports NFS so there are users that want support for swapping over NFS despite any performance concern. Some distributions currently carry patches that support swapping over NFS but it would be preferable to support it in the mainline kernel. Patch 1 avoids a stream-specific deadlock that potentially affects TCP. Patch 2 is a small modification to SELinux to avoid using PFMEMALLOC reserves. Patch 3 adds three helpers for filesystems to handle swap cache pages. For example, page_file_mapping() returns page->mapping for file-backed pages and the address_space of the underlying swap file for swap cache pages. Patch 4 adds two address_space_operations to allow a filesystem to pin all metadata relevant to a swapfile in memory. Upon successful activation, the swapfile is marked SWP_FILE and the address space operation ->direct_IO is used for writing and ->readpage for reading in swap pages. Patch 5 notes that patch 3 is bolting filesystem-specific-swapfile-support onto the side and that the default handlers have different information to what is available to the filesystem. This patch refactors the code so that there are generic handlers for each of the new address_space operations. Patch 6 adds an API to allow a vector of kernel addresses to be translated to struct pages and pinned for IO. Patch 7 adds support for using highmem pages for swap by kmapping the pages before calling the direct_IO handler. Patch 8 updates NFS to use the helpers from patch 3 where necessary. Patch 9 avoids setting PF_private on PG_swapcache pages within NFS. Patch 10 implements the new swapfile-related address_space operations for NFS and teaches the direct IO handler how to manage kernel addresses. Patch 11 prevents page allocator recursions in NFS by using GFP_NOIO where appropriate. Patch 12 fixes a NULL pointer dereference that occurs when using swap-over-NFS. With the patches applied, it is possible to mount a swapfile that is on an NFS filesystem. Swap performance is not great with a swap stress test taking roughly twice as long to complete than if the swap device was backed by NBD. This patch: netvm: prevent a stream-specific deadlock It could happen that all !SOCK_MEMALLOC sockets have buffered so much data that we're over the global rmem limit. This will prevent SOCK_MEMALLOC buffers from receiving data, which will prevent userspace from running, which is needed to reduce the buffered data. Fix this by exempting the SOCK_MEMALLOC sockets from the rmem limit. Once this change it applied, it is important that sockets that set SOCK_MEMALLOC do not clear the flag until the socket is being torn down. If this happens, a warning is generated and the tokens reclaimed to avoid accounting errors until the bug is fixed. [davem@davemloft.net: Warning about clearing SOCK_MEMALLOC] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Mel Gorman <mgorman@suse.de> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Rik van Riel <riel@redhat.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Cc: Neil Brown <neilb@suse.de> Cc: Christoph Hellwig <hch@infradead.org> Cc: Mike Christie <michaelc@cs.wisc.edu> Cc: Eric B Munson <emunson@mgebm.net> Cc: Sebastian Andrzej Siewior <sebastian@breakpoint.cc> Cc: Mel Gorman <mgorman@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-07-31 23:44:41 +00:00
*/
net, swap: Remove a warning and clarify why sk_mem_reclaim is required when deactivating swap Jeff Layton reported the following; [ 74.232485] ------------[ cut here ]------------ [ 74.233354] WARNING: CPU: 2 PID: 754 at net/core/sock.c:364 sk_clear_memalloc+0x51/0x80() [ 74.234790] Modules linked in: cts rpcsec_gss_krb5 nfsv4 dns_resolver nfs fscache xfs libcrc32c snd_hda_codec_generic snd_hda_intel snd_hda_controller snd_hda_codec snd_hda_core snd_hwdep snd_seq snd_seq_device nfsd snd_pcm snd_timer snd e1000 ppdev parport_pc joydev parport pvpanic soundcore floppy serio_raw i2c_piix4 pcspkr nfs_acl lockd virtio_balloon acpi_cpufreq auth_rpcgss grace sunrpc qxl drm_kms_helper ttm drm virtio_console virtio_blk virtio_pci ata_generic virtio_ring pata_acpi virtio [ 74.243599] CPU: 2 PID: 754 Comm: swapoff Not tainted 4.1.0-rc6+ #5 [ 74.244635] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 [ 74.245546] 0000000000000000 0000000079e69e31 ffff8800d066bde8 ffffffff8179263d [ 74.246786] 0000000000000000 0000000000000000 ffff8800d066be28 ffffffff8109e6fa [ 74.248175] 0000000000000000 ffff880118d48000 ffff8800d58f5c08 ffff880036e380a8 [ 74.249483] Call Trace: [ 74.249872] [<ffffffff8179263d>] dump_stack+0x45/0x57 [ 74.250703] [<ffffffff8109e6fa>] warn_slowpath_common+0x8a/0xc0 [ 74.251655] [<ffffffff8109e82a>] warn_slowpath_null+0x1a/0x20 [ 74.252585] [<ffffffff81661241>] sk_clear_memalloc+0x51/0x80 [ 74.253519] [<ffffffffa0116c72>] xs_disable_swap+0x42/0x80 [sunrpc] [ 74.254537] [<ffffffffa01109de>] rpc_clnt_swap_deactivate+0x7e/0xc0 [sunrpc] [ 74.255610] [<ffffffffa03e4fd7>] nfs_swap_deactivate+0x27/0x30 [nfs] [ 74.256582] [<ffffffff811e99d4>] destroy_swap_extents+0x74/0x80 [ 74.257496] [<ffffffff811ecb52>] SyS_swapoff+0x222/0x5c0 [ 74.258318] [<ffffffff81023f27>] ? syscall_trace_leave+0xc7/0x140 [ 74.259253] [<ffffffff81798dae>] system_call_fastpath+0x12/0x71 [ 74.260158] ---[ end trace 2530722966429f10 ]--- The warning in question was unnecessary but with Jeff's series the rules are also clearer. This patch removes the warning and updates the comment to explain why sk_mem_reclaim() may still be called. [jlayton: remove if (sk->sk_forward_alloc) conditional. As Leon points out that it's not needed.] Cc: Leon Romanovsky <leon@leon.nu> Signed-off-by: Mel Gorman <mgorman@suse.de> Signed-off-by: Jeff Layton <jeff.layton@primarydata.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-06-11 01:02:04 +00:00
sk_mem_reclaim(sk);
}
EXPORT_SYMBOL_GPL(sk_clear_memalloc);
int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
{
int ret;
unsigned int noreclaim_flag;
/* these should have been dropped before queueing */
BUG_ON(!sock_flag(sk, SOCK_MEMALLOC));
noreclaim_flag = memalloc_noreclaim_save();
ret = sk->sk_backlog_rcv(sk, skb);
memalloc_noreclaim_restore(noreclaim_flag);
return ret;
}
EXPORT_SYMBOL(__sk_backlog_rcv);
static int sock_get_timeout(long timeo, void *optval, bool old_timeval)
{
struct __kernel_sock_timeval tv;
if (timeo == MAX_SCHEDULE_TIMEOUT) {
tv.tv_sec = 0;
tv.tv_usec = 0;
} else {
tv.tv_sec = timeo / HZ;
tv.tv_usec = ((timeo % HZ) * USEC_PER_SEC) / HZ;
}
if (old_timeval && in_compat_syscall() && !COMPAT_USE_64BIT_TIME) {
struct old_timeval32 tv32 = { tv.tv_sec, tv.tv_usec };
*(struct old_timeval32 *)optval = tv32;
return sizeof(tv32);
}
if (old_timeval) {
struct __kernel_old_timeval old_tv;
old_tv.tv_sec = tv.tv_sec;
old_tv.tv_usec = tv.tv_usec;
*(struct __kernel_old_timeval *)optval = old_tv;
return sizeof(old_tv);
}
*(struct __kernel_sock_timeval *)optval = tv;
return sizeof(tv);
}
static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen,
bool old_timeval)
{
struct __kernel_sock_timeval tv;
if (old_timeval && in_compat_syscall() && !COMPAT_USE_64BIT_TIME) {
struct old_timeval32 tv32;
if (optlen < sizeof(tv32))
return -EINVAL;
if (copy_from_sockptr(&tv32, optval, sizeof(tv32)))
return -EFAULT;
tv.tv_sec = tv32.tv_sec;
tv.tv_usec = tv32.tv_usec;
} else if (old_timeval) {
struct __kernel_old_timeval old_tv;
if (optlen < sizeof(old_tv))
return -EINVAL;
if (copy_from_sockptr(&old_tv, optval, sizeof(old_tv)))
return -EFAULT;
tv.tv_sec = old_tv.tv_sec;
tv.tv_usec = old_tv.tv_usec;
} else {
if (optlen < sizeof(tv))
return -EINVAL;
if (copy_from_sockptr(&tv, optval, sizeof(tv)))
return -EFAULT;
}
if (tv.tv_usec < 0 || tv.tv_usec >= USEC_PER_SEC)
return -EDOM;
if (tv.tv_sec < 0) {
static int warned __read_mostly;
*timeo_p = 0;
if (warned < 10 && net_ratelimit()) {
warned++;
pr_info("%s: `%s' (pid %d) tries to set negative timeout\n",
__func__, current->comm, task_pid_nr(current));
}
return 0;
}
*timeo_p = MAX_SCHEDULE_TIMEOUT;
if (tv.tv_sec == 0 && tv.tv_usec == 0)
return 0;
if (tv.tv_sec < (MAX_SCHEDULE_TIMEOUT / HZ - 1))
*timeo_p = tv.tv_sec * HZ + DIV_ROUND_UP((unsigned long)tv.tv_usec, USEC_PER_SEC / HZ);
return 0;
}
static bool sock_needs_netstamp(const struct sock *sk)
{
switch (sk->sk_family) {
case AF_UNSPEC:
case AF_UNIX:
return false;
default:
return true;
}
}
static void sock_disable_timestamp(struct sock *sk, unsigned long flags)
{
if (sk->sk_flags & flags) {
sk->sk_flags &= ~flags;
if (sock_needs_netstamp(sk) &&
!(sk->sk_flags & SK_FLAGS_TIMESTAMP))
net_disable_timestamp();
}
}
int __sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
[NET]: deinline 200+ byte inlines in sock.h Sizes in bytes (allyesconfig, i386) and files where those inlines are used: 238 sock_queue_rcv_skb 2.6.16/net/x25/x25_in.o 238 sock_queue_rcv_skb 2.6.16/net/rose/rose_in.o 238 sock_queue_rcv_skb 2.6.16/net/packet/af_packet.o 238 sock_queue_rcv_skb 2.6.16/net/netrom/nr_in.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_sap.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_conn.o 238 sock_queue_rcv_skb 2.6.16/net/irda/af_irda.o 238 sock_queue_rcv_skb 2.6.16/net/ipx/af_ipx.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/ipmr.o 238 sock_queue_rcv_skb 2.6.16/net/econet/econet.o 238 sock_queue_rcv_skb 2.6.16/net/econet/af_econet.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/sco.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/l2cap.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/hci_sock.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/ax25_in.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/af_ax25.o 238 sock_queue_rcv_skb 2.6.16/net/appletalk/ddp.o 238 sock_queue_rcv_skb 2.6.16/drivers/net/pppoe.o 276 sk_receive_skb 2.6.16/net/decnet/dn_nsp_in.o 276 sk_receive_skb 2.6.16/net/dccp/ipv6.o 276 sk_receive_skb 2.6.16/net/dccp/ipv4.o 276 sk_receive_skb 2.6.16/net/dccp/dccp_ipv6.o 276 sk_receive_skb 2.6.16/drivers/net/pppoe.o 209 sk_dst_check 2.6.16/net/ipv6/ip6_output.o 209 sk_dst_check 2.6.16/net/ipv4/udp.o 209 sk_dst_check 2.6.16/net/decnet/dn_nsp_out.o Large inlines with multiple callers: Size Uses Wasted Name and definition ===== ==== ====== ================================================ 238 21 4360 sock_queue_rcv_skb include/net/sock.h 109 10 801 sock_recv_timestamp include/net/sock.h 276 4 768 sk_receive_skb include/net/sock.h 94 8 518 __sk_dst_check include/net/sock.h 209 3 378 sk_dst_check include/net/sock.h 131 4 333 sk_setup_caps include/net/sock.h 152 2 132 sk_stream_alloc_pskb include/net/sock.h 125 2 105 sk_stream_writequeue_purge include/net/sock.h Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-28 09:08:21 +00:00
{
net: Generalize socket rx gap / receive queue overflow cmsg Create a new socket level option to report number of queue overflows Recently I augmented the AF_PACKET protocol to report the number of frames lost on the socket receive queue between any two enqueued frames. This value was exported via a SOL_PACKET level cmsg. AFter I completed that work it was requested that this feature be generalized so that any datagram oriented socket could make use of this option. As such I've created this patch, It creates a new SOL_SOCKET level option called SO_RXQ_OVFL, which when enabled exports a SOL_SOCKET level cmsg that reports the nubmer of times the sk_receive_queue overflowed between any two given frames. It also augments the AF_PACKET protocol to take advantage of this new feature (as it previously did not touch sk->sk_drops, which this patch uses to record the overflow count). Tested successfully by me. Notes: 1) Unlike my previous patch, this patch simply records the sk_drops value, which is not a number of drops between packets, but rather a total number of drops. Deltas must be computed in user space. 2) While this patch currently works with datagram oriented protocols, it will also be accepted by non-datagram oriented protocols. I'm not sure if thats agreeable to everyone, but my argument in favor of doing so is that, for those protocols which aren't applicable to this option, sk_drops will always be zero, and reporting no drops on a receive queue that isn't used for those non-participating protocols seems reasonable to me. This also saves us having to code in a per-protocol opt in mechanism. 3) This applies cleanly to net-next assuming that commit 977750076d98c7ff6cbda51858bb5a5894a9d9ab (my af packet cmsg patch) is reverted Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-10-12 20:26:31 +00:00
unsigned long flags;
struct sk_buff_head *list = &sk->sk_receive_queue;
[NET]: deinline 200+ byte inlines in sock.h Sizes in bytes (allyesconfig, i386) and files where those inlines are used: 238 sock_queue_rcv_skb 2.6.16/net/x25/x25_in.o 238 sock_queue_rcv_skb 2.6.16/net/rose/rose_in.o 238 sock_queue_rcv_skb 2.6.16/net/packet/af_packet.o 238 sock_queue_rcv_skb 2.6.16/net/netrom/nr_in.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_sap.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_conn.o 238 sock_queue_rcv_skb 2.6.16/net/irda/af_irda.o 238 sock_queue_rcv_skb 2.6.16/net/ipx/af_ipx.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/ipmr.o 238 sock_queue_rcv_skb 2.6.16/net/econet/econet.o 238 sock_queue_rcv_skb 2.6.16/net/econet/af_econet.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/sco.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/l2cap.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/hci_sock.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/ax25_in.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/af_ax25.o 238 sock_queue_rcv_skb 2.6.16/net/appletalk/ddp.o 238 sock_queue_rcv_skb 2.6.16/drivers/net/pppoe.o 276 sk_receive_skb 2.6.16/net/decnet/dn_nsp_in.o 276 sk_receive_skb 2.6.16/net/dccp/ipv6.o 276 sk_receive_skb 2.6.16/net/dccp/ipv4.o 276 sk_receive_skb 2.6.16/net/dccp/dccp_ipv6.o 276 sk_receive_skb 2.6.16/drivers/net/pppoe.o 209 sk_dst_check 2.6.16/net/ipv6/ip6_output.o 209 sk_dst_check 2.6.16/net/ipv4/udp.o 209 sk_dst_check 2.6.16/net/decnet/dn_nsp_out.o Large inlines with multiple callers: Size Uses Wasted Name and definition ===== ==== ====== ================================================ 238 21 4360 sock_queue_rcv_skb include/net/sock.h 109 10 801 sock_recv_timestamp include/net/sock.h 276 4 768 sk_receive_skb include/net/sock.h 94 8 518 __sk_dst_check include/net/sock.h 209 3 378 sk_dst_check include/net/sock.h 131 4 333 sk_setup_caps include/net/sock.h 152 2 132 sk_stream_alloc_pskb include/net/sock.h 125 2 105 sk_stream_writequeue_purge include/net/sock.h Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-28 09:08:21 +00:00
if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) {
atomic_inc(&sk->sk_drops);
trace_sock_rcvqueue_full(sk, skb);
return -ENOMEM;
[NET]: deinline 200+ byte inlines in sock.h Sizes in bytes (allyesconfig, i386) and files where those inlines are used: 238 sock_queue_rcv_skb 2.6.16/net/x25/x25_in.o 238 sock_queue_rcv_skb 2.6.16/net/rose/rose_in.o 238 sock_queue_rcv_skb 2.6.16/net/packet/af_packet.o 238 sock_queue_rcv_skb 2.6.16/net/netrom/nr_in.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_sap.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_conn.o 238 sock_queue_rcv_skb 2.6.16/net/irda/af_irda.o 238 sock_queue_rcv_skb 2.6.16/net/ipx/af_ipx.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/ipmr.o 238 sock_queue_rcv_skb 2.6.16/net/econet/econet.o 238 sock_queue_rcv_skb 2.6.16/net/econet/af_econet.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/sco.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/l2cap.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/hci_sock.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/ax25_in.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/af_ax25.o 238 sock_queue_rcv_skb 2.6.16/net/appletalk/ddp.o 238 sock_queue_rcv_skb 2.6.16/drivers/net/pppoe.o 276 sk_receive_skb 2.6.16/net/decnet/dn_nsp_in.o 276 sk_receive_skb 2.6.16/net/dccp/ipv6.o 276 sk_receive_skb 2.6.16/net/dccp/ipv4.o 276 sk_receive_skb 2.6.16/net/dccp/dccp_ipv6.o 276 sk_receive_skb 2.6.16/drivers/net/pppoe.o 209 sk_dst_check 2.6.16/net/ipv6/ip6_output.o 209 sk_dst_check 2.6.16/net/ipv4/udp.o 209 sk_dst_check 2.6.16/net/decnet/dn_nsp_out.o Large inlines with multiple callers: Size Uses Wasted Name and definition ===== ==== ====== ================================================ 238 21 4360 sock_queue_rcv_skb include/net/sock.h 109 10 801 sock_recv_timestamp include/net/sock.h 276 4 768 sk_receive_skb include/net/sock.h 94 8 518 __sk_dst_check include/net/sock.h 209 3 378 sk_dst_check include/net/sock.h 131 4 333 sk_setup_caps include/net/sock.h 152 2 132 sk_stream_alloc_pskb include/net/sock.h 125 2 105 sk_stream_writequeue_purge include/net/sock.h Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-28 09:08:21 +00:00
}
netvm: prevent a stream-specific deadlock This patch series is based on top of "Swap-over-NBD without deadlocking v15" as it depends on the same reservation of PF_MEMALLOC reserves logic. When a user or administrator requires swap for their application, they create a swap partition and file, format it with mkswap and activate it with swapon. In diskless systems this is not an option so if swap if required then swapping over the network is considered. The two likely scenarios are when blade servers are used as part of a cluster where the form factor or maintenance costs do not allow the use of disks and thin clients. The Linux Terminal Server Project recommends the use of the Network Block Device (NBD) for swap but this is not always an option. There is no guarantee that the network attached storage (NAS) device is running Linux or supports NBD. However, it is likely that it supports NFS so there are users that want support for swapping over NFS despite any performance concern. Some distributions currently carry patches that support swapping over NFS but it would be preferable to support it in the mainline kernel. Patch 1 avoids a stream-specific deadlock that potentially affects TCP. Patch 2 is a small modification to SELinux to avoid using PFMEMALLOC reserves. Patch 3 adds three helpers for filesystems to handle swap cache pages. For example, page_file_mapping() returns page->mapping for file-backed pages and the address_space of the underlying swap file for swap cache pages. Patch 4 adds two address_space_operations to allow a filesystem to pin all metadata relevant to a swapfile in memory. Upon successful activation, the swapfile is marked SWP_FILE and the address space operation ->direct_IO is used for writing and ->readpage for reading in swap pages. Patch 5 notes that patch 3 is bolting filesystem-specific-swapfile-support onto the side and that the default handlers have different information to what is available to the filesystem. This patch refactors the code so that there are generic handlers for each of the new address_space operations. Patch 6 adds an API to allow a vector of kernel addresses to be translated to struct pages and pinned for IO. Patch 7 adds support for using highmem pages for swap by kmapping the pages before calling the direct_IO handler. Patch 8 updates NFS to use the helpers from patch 3 where necessary. Patch 9 avoids setting PF_private on PG_swapcache pages within NFS. Patch 10 implements the new swapfile-related address_space operations for NFS and teaches the direct IO handler how to manage kernel addresses. Patch 11 prevents page allocator recursions in NFS by using GFP_NOIO where appropriate. Patch 12 fixes a NULL pointer dereference that occurs when using swap-over-NFS. With the patches applied, it is possible to mount a swapfile that is on an NFS filesystem. Swap performance is not great with a swap stress test taking roughly twice as long to complete than if the swap device was backed by NBD. This patch: netvm: prevent a stream-specific deadlock It could happen that all !SOCK_MEMALLOC sockets have buffered so much data that we're over the global rmem limit. This will prevent SOCK_MEMALLOC buffers from receiving data, which will prevent userspace from running, which is needed to reduce the buffered data. Fix this by exempting the SOCK_MEMALLOC sockets from the rmem limit. Once this change it applied, it is important that sockets that set SOCK_MEMALLOC do not clear the flag until the socket is being torn down. If this happens, a warning is generated and the tokens reclaimed to avoid accounting errors until the bug is fixed. [davem@davemloft.net: Warning about clearing SOCK_MEMALLOC] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Mel Gorman <mgorman@suse.de> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Rik van Riel <riel@redhat.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Cc: Neil Brown <neilb@suse.de> Cc: Christoph Hellwig <hch@infradead.org> Cc: Mike Christie <michaelc@cs.wisc.edu> Cc: Eric B Munson <emunson@mgebm.net> Cc: Sebastian Andrzej Siewior <sebastian@breakpoint.cc> Cc: Mel Gorman <mgorman@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-07-31 23:44:41 +00:00
if (!sk_rmem_schedule(sk, skb, skb->truesize)) {
atomic_inc(&sk->sk_drops);
return -ENOBUFS;
[NET] CORE: Introducing new memory accounting interface. This patch introduces new memory accounting functions for each network protocol. Most of them are renamed from memory accounting functions for stream protocols. At the same time, some stream memory accounting functions are removed since other functions do same thing. Renaming: sk_stream_free_skb() -> sk_wmem_free_skb() __sk_stream_mem_reclaim() -> __sk_mem_reclaim() sk_stream_mem_reclaim() -> sk_mem_reclaim() sk_stream_mem_schedule -> __sk_mem_schedule() sk_stream_pages() -> sk_mem_pages() sk_stream_rmem_schedule() -> sk_rmem_schedule() sk_stream_wmem_schedule() -> sk_wmem_schedule() sk_charge_skb() -> sk_mem_charge() Removeing sk_stream_rfree(): consolidates into sock_rfree() sk_stream_set_owner_r(): consolidates into skb_set_owner_r() sk_stream_mem_schedule() The following functions are added. sk_has_account(): check if the protocol supports accounting sk_mem_uncharge(): do the opposite of sk_mem_charge() In addition, to achieve consolidation, updating sk_wmem_queued is removed from sk_mem_charge(). Next, to consolidate memory accounting functions, this patch adds memory accounting calls to network core functions. Moreover, present memory accounting call is renamed to new accounting call. Finally we replace present memory accounting calls with new interface in TCP and SCTP. Signed-off-by: Takahiro Yasui <tyasui@redhat.com> Signed-off-by: Hideo Aoki <haoki@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-31 08:11:19 +00:00
}
[NET]: deinline 200+ byte inlines in sock.h Sizes in bytes (allyesconfig, i386) and files where those inlines are used: 238 sock_queue_rcv_skb 2.6.16/net/x25/x25_in.o 238 sock_queue_rcv_skb 2.6.16/net/rose/rose_in.o 238 sock_queue_rcv_skb 2.6.16/net/packet/af_packet.o 238 sock_queue_rcv_skb 2.6.16/net/netrom/nr_in.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_sap.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_conn.o 238 sock_queue_rcv_skb 2.6.16/net/irda/af_irda.o 238 sock_queue_rcv_skb 2.6.16/net/ipx/af_ipx.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/ipmr.o 238 sock_queue_rcv_skb 2.6.16/net/econet/econet.o 238 sock_queue_rcv_skb 2.6.16/net/econet/af_econet.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/sco.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/l2cap.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/hci_sock.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/ax25_in.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/af_ax25.o 238 sock_queue_rcv_skb 2.6.16/net/appletalk/ddp.o 238 sock_queue_rcv_skb 2.6.16/drivers/net/pppoe.o 276 sk_receive_skb 2.6.16/net/decnet/dn_nsp_in.o 276 sk_receive_skb 2.6.16/net/dccp/ipv6.o 276 sk_receive_skb 2.6.16/net/dccp/ipv4.o 276 sk_receive_skb 2.6.16/net/dccp/dccp_ipv6.o 276 sk_receive_skb 2.6.16/drivers/net/pppoe.o 209 sk_dst_check 2.6.16/net/ipv6/ip6_output.o 209 sk_dst_check 2.6.16/net/ipv4/udp.o 209 sk_dst_check 2.6.16/net/decnet/dn_nsp_out.o Large inlines with multiple callers: Size Uses Wasted Name and definition ===== ==== ====== ================================================ 238 21 4360 sock_queue_rcv_skb include/net/sock.h 109 10 801 sock_recv_timestamp include/net/sock.h 276 4 768 sk_receive_skb include/net/sock.h 94 8 518 __sk_dst_check include/net/sock.h 209 3 378 sk_dst_check include/net/sock.h 131 4 333 sk_setup_caps include/net/sock.h 152 2 132 sk_stream_alloc_pskb include/net/sock.h 125 2 105 sk_stream_writequeue_purge include/net/sock.h Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-28 09:08:21 +00:00
skb->dev = NULL;
skb_set_owner_r(skb, sk);
/* we escape from rcu protected region, make sure we dont leak
* a norefcounted dst
*/
skb_dst_force(skb);
net: Generalize socket rx gap / receive queue overflow cmsg Create a new socket level option to report number of queue overflows Recently I augmented the AF_PACKET protocol to report the number of frames lost on the socket receive queue between any two enqueued frames. This value was exported via a SOL_PACKET level cmsg. AFter I completed that work it was requested that this feature be generalized so that any datagram oriented socket could make use of this option. As such I've created this patch, It creates a new SOL_SOCKET level option called SO_RXQ_OVFL, which when enabled exports a SOL_SOCKET level cmsg that reports the nubmer of times the sk_receive_queue overflowed between any two given frames. It also augments the AF_PACKET protocol to take advantage of this new feature (as it previously did not touch sk->sk_drops, which this patch uses to record the overflow count). Tested successfully by me. Notes: 1) Unlike my previous patch, this patch simply records the sk_drops value, which is not a number of drops between packets, but rather a total number of drops. Deltas must be computed in user space. 2) While this patch currently works with datagram oriented protocols, it will also be accepted by non-datagram oriented protocols. I'm not sure if thats agreeable to everyone, but my argument in favor of doing so is that, for those protocols which aren't applicable to this option, sk_drops will always be zero, and reporting no drops on a receive queue that isn't used for those non-participating protocols seems reasonable to me. This also saves us having to code in a per-protocol opt in mechanism. 3) This applies cleanly to net-next assuming that commit 977750076d98c7ff6cbda51858bb5a5894a9d9ab (my af packet cmsg patch) is reverted Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-10-12 20:26:31 +00:00
spin_lock_irqsave(&list->lock, flags);
sock_skb_set_dropcount(sk, skb);
net: Generalize socket rx gap / receive queue overflow cmsg Create a new socket level option to report number of queue overflows Recently I augmented the AF_PACKET protocol to report the number of frames lost on the socket receive queue between any two enqueued frames. This value was exported via a SOL_PACKET level cmsg. AFter I completed that work it was requested that this feature be generalized so that any datagram oriented socket could make use of this option. As such I've created this patch, It creates a new SOL_SOCKET level option called SO_RXQ_OVFL, which when enabled exports a SOL_SOCKET level cmsg that reports the nubmer of times the sk_receive_queue overflowed between any two given frames. It also augments the AF_PACKET protocol to take advantage of this new feature (as it previously did not touch sk->sk_drops, which this patch uses to record the overflow count). Tested successfully by me. Notes: 1) Unlike my previous patch, this patch simply records the sk_drops value, which is not a number of drops between packets, but rather a total number of drops. Deltas must be computed in user space. 2) While this patch currently works with datagram oriented protocols, it will also be accepted by non-datagram oriented protocols. I'm not sure if thats agreeable to everyone, but my argument in favor of doing so is that, for those protocols which aren't applicable to this option, sk_drops will always be zero, and reporting no drops on a receive queue that isn't used for those non-participating protocols seems reasonable to me. This also saves us having to code in a per-protocol opt in mechanism. 3) This applies cleanly to net-next assuming that commit 977750076d98c7ff6cbda51858bb5a5894a9d9ab (my af packet cmsg patch) is reverted Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-10-12 20:26:31 +00:00
__skb_queue_tail(list, skb);
spin_unlock_irqrestore(&list->lock, flags);
[NET]: deinline 200+ byte inlines in sock.h Sizes in bytes (allyesconfig, i386) and files where those inlines are used: 238 sock_queue_rcv_skb 2.6.16/net/x25/x25_in.o 238 sock_queue_rcv_skb 2.6.16/net/rose/rose_in.o 238 sock_queue_rcv_skb 2.6.16/net/packet/af_packet.o 238 sock_queue_rcv_skb 2.6.16/net/netrom/nr_in.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_sap.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_conn.o 238 sock_queue_rcv_skb 2.6.16/net/irda/af_irda.o 238 sock_queue_rcv_skb 2.6.16/net/ipx/af_ipx.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/ipmr.o 238 sock_queue_rcv_skb 2.6.16/net/econet/econet.o 238 sock_queue_rcv_skb 2.6.16/net/econet/af_econet.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/sco.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/l2cap.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/hci_sock.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/ax25_in.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/af_ax25.o 238 sock_queue_rcv_skb 2.6.16/net/appletalk/ddp.o 238 sock_queue_rcv_skb 2.6.16/drivers/net/pppoe.o 276 sk_receive_skb 2.6.16/net/decnet/dn_nsp_in.o 276 sk_receive_skb 2.6.16/net/dccp/ipv6.o 276 sk_receive_skb 2.6.16/net/dccp/ipv4.o 276 sk_receive_skb 2.6.16/net/dccp/dccp_ipv6.o 276 sk_receive_skb 2.6.16/drivers/net/pppoe.o 209 sk_dst_check 2.6.16/net/ipv6/ip6_output.o 209 sk_dst_check 2.6.16/net/ipv4/udp.o 209 sk_dst_check 2.6.16/net/decnet/dn_nsp_out.o Large inlines with multiple callers: Size Uses Wasted Name and definition ===== ==== ====== ================================================ 238 21 4360 sock_queue_rcv_skb include/net/sock.h 109 10 801 sock_recv_timestamp include/net/sock.h 276 4 768 sk_receive_skb include/net/sock.h 94 8 518 __sk_dst_check include/net/sock.h 209 3 378 sk_dst_check include/net/sock.h 131 4 333 sk_setup_caps include/net/sock.h 152 2 132 sk_stream_alloc_pskb include/net/sock.h 125 2 105 sk_stream_writequeue_purge include/net/sock.h Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-28 09:08:21 +00:00
if (!sock_flag(sk, SOCK_DEAD))
sk->sk_data_ready(sk);
return 0;
[NET]: deinline 200+ byte inlines in sock.h Sizes in bytes (allyesconfig, i386) and files where those inlines are used: 238 sock_queue_rcv_skb 2.6.16/net/x25/x25_in.o 238 sock_queue_rcv_skb 2.6.16/net/rose/rose_in.o 238 sock_queue_rcv_skb 2.6.16/net/packet/af_packet.o 238 sock_queue_rcv_skb 2.6.16/net/netrom/nr_in.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_sap.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_conn.o 238 sock_queue_rcv_skb 2.6.16/net/irda/af_irda.o 238 sock_queue_rcv_skb 2.6.16/net/ipx/af_ipx.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/ipmr.o 238 sock_queue_rcv_skb 2.6.16/net/econet/econet.o 238 sock_queue_rcv_skb 2.6.16/net/econet/af_econet.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/sco.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/l2cap.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/hci_sock.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/ax25_in.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/af_ax25.o 238 sock_queue_rcv_skb 2.6.16/net/appletalk/ddp.o 238 sock_queue_rcv_skb 2.6.16/drivers/net/pppoe.o 276 sk_receive_skb 2.6.16/net/decnet/dn_nsp_in.o 276 sk_receive_skb 2.6.16/net/dccp/ipv6.o 276 sk_receive_skb 2.6.16/net/dccp/ipv4.o 276 sk_receive_skb 2.6.16/net/dccp/dccp_ipv6.o 276 sk_receive_skb 2.6.16/drivers/net/pppoe.o 209 sk_dst_check 2.6.16/net/ipv6/ip6_output.o 209 sk_dst_check 2.6.16/net/ipv4/udp.o 209 sk_dst_check 2.6.16/net/decnet/dn_nsp_out.o Large inlines with multiple callers: Size Uses Wasted Name and definition ===== ==== ====== ================================================ 238 21 4360 sock_queue_rcv_skb include/net/sock.h 109 10 801 sock_recv_timestamp include/net/sock.h 276 4 768 sk_receive_skb include/net/sock.h 94 8 518 __sk_dst_check include/net/sock.h 209 3 378 sk_dst_check include/net/sock.h 131 4 333 sk_setup_caps include/net/sock.h 152 2 132 sk_stream_alloc_pskb include/net/sock.h 125 2 105 sk_stream_writequeue_purge include/net/sock.h Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-28 09:08:21 +00:00
}
EXPORT_SYMBOL(__sock_queue_rcv_skb);
int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
int err;
err = sk_filter(sk, skb);
if (err)
return err;
return __sock_queue_rcv_skb(sk, skb);
}
[NET]: deinline 200+ byte inlines in sock.h Sizes in bytes (allyesconfig, i386) and files where those inlines are used: 238 sock_queue_rcv_skb 2.6.16/net/x25/x25_in.o 238 sock_queue_rcv_skb 2.6.16/net/rose/rose_in.o 238 sock_queue_rcv_skb 2.6.16/net/packet/af_packet.o 238 sock_queue_rcv_skb 2.6.16/net/netrom/nr_in.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_sap.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_conn.o 238 sock_queue_rcv_skb 2.6.16/net/irda/af_irda.o 238 sock_queue_rcv_skb 2.6.16/net/ipx/af_ipx.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/ipmr.o 238 sock_queue_rcv_skb 2.6.16/net/econet/econet.o 238 sock_queue_rcv_skb 2.6.16/net/econet/af_econet.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/sco.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/l2cap.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/hci_sock.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/ax25_in.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/af_ax25.o 238 sock_queue_rcv_skb 2.6.16/net/appletalk/ddp.o 238 sock_queue_rcv_skb 2.6.16/drivers/net/pppoe.o 276 sk_receive_skb 2.6.16/net/decnet/dn_nsp_in.o 276 sk_receive_skb 2.6.16/net/dccp/ipv6.o 276 sk_receive_skb 2.6.16/net/dccp/ipv4.o 276 sk_receive_skb 2.6.16/net/dccp/dccp_ipv6.o 276 sk_receive_skb 2.6.16/drivers/net/pppoe.o 209 sk_dst_check 2.6.16/net/ipv6/ip6_output.o 209 sk_dst_check 2.6.16/net/ipv4/udp.o 209 sk_dst_check 2.6.16/net/decnet/dn_nsp_out.o Large inlines with multiple callers: Size Uses Wasted Name and definition ===== ==== ====== ================================================ 238 21 4360 sock_queue_rcv_skb include/net/sock.h 109 10 801 sock_recv_timestamp include/net/sock.h 276 4 768 sk_receive_skb include/net/sock.h 94 8 518 __sk_dst_check include/net/sock.h 209 3 378 sk_dst_check include/net/sock.h 131 4 333 sk_setup_caps include/net/sock.h 152 2 132 sk_stream_alloc_pskb include/net/sock.h 125 2 105 sk_stream_writequeue_purge include/net/sock.h Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-28 09:08:21 +00:00
EXPORT_SYMBOL(sock_queue_rcv_skb);
int __sk_receive_skb(struct sock *sk, struct sk_buff *skb,
dccp: do not release listeners too soon Andrey Konovalov reported following error while fuzzing with syzkaller : IPv4: Attempt to release alive inet socket ffff880068e98940 kasan: CONFIG_KASAN_INLINE enabled kasan: GPF could be caused by NULL-ptr deref or user memory access general protection fault: 0000 [#1] SMP KASAN Modules linked in: CPU: 1 PID: 3905 Comm: a.out Not tainted 4.9.0-rc3+ #333 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 task: ffff88006b9e0000 task.stack: ffff880068770000 RIP: 0010:[<ffffffff819ead5f>] [<ffffffff819ead5f>] selinux_socket_sock_rcv_skb+0xff/0x6a0 security/selinux/hooks.c:4639 RSP: 0018:ffff8800687771c8 EFLAGS: 00010202 RAX: ffff88006b9e0000 RBX: 1ffff1000d0eee3f RCX: 1ffff1000d1d312a RDX: 1ffff1000d1d31a6 RSI: dffffc0000000000 RDI: 0000000000000010 RBP: ffff880068777360 R08: 0000000000000000 R09: 0000000000000002 R10: dffffc0000000000 R11: 0000000000000006 R12: ffff880068e98940 R13: 0000000000000002 R14: ffff880068777338 R15: 0000000000000000 FS: 00007f00ff760700(0000) GS:ffff88006cd00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020008000 CR3: 000000006a308000 CR4: 00000000000006e0 Stack: ffff8800687771e0 ffffffff812508a5 ffff8800686f3168 0000000000000007 ffff88006ac8cdfc ffff8800665ea500 0000000041b58ab3 ffffffff847b5480 ffffffff819eac60 ffff88006b9e0860 ffff88006b9e0868 ffff88006b9e07f0 Call Trace: [<ffffffff819c8dd5>] security_sock_rcv_skb+0x75/0xb0 security/security.c:1317 [<ffffffff82c2a9e7>] sk_filter_trim_cap+0x67/0x10e0 net/core/filter.c:81 [<ffffffff82b81e60>] __sk_receive_skb+0x30/0xa00 net/core/sock.c:460 [<ffffffff838bbf12>] dccp_v4_rcv+0xdb2/0x1910 net/dccp/ipv4.c:873 [<ffffffff83069d22>] ip_local_deliver_finish+0x332/0xad0 net/ipv4/ip_input.c:216 [< inline >] NF_HOOK_THRESH ./include/linux/netfilter.h:232 [< inline >] NF_HOOK ./include/linux/netfilter.h:255 [<ffffffff8306abd2>] ip_local_deliver+0x1c2/0x4b0 net/ipv4/ip_input.c:257 [< inline >] dst_input ./include/net/dst.h:507 [<ffffffff83068500>] ip_rcv_finish+0x750/0x1c40 net/ipv4/ip_input.c:396 [< inline >] NF_HOOK_THRESH ./include/linux/netfilter.h:232 [< inline >] NF_HOOK ./include/linux/netfilter.h:255 [<ffffffff8306b82f>] ip_rcv+0x96f/0x12f0 net/ipv4/ip_input.c:487 [<ffffffff82bd9fb7>] __netif_receive_skb_core+0x1897/0x2a50 net/core/dev.c:4213 [<ffffffff82bdb19a>] __netif_receive_skb+0x2a/0x170 net/core/dev.c:4251 [<ffffffff82bdb493>] netif_receive_skb_internal+0x1b3/0x390 net/core/dev.c:4279 [<ffffffff82bdb6b8>] netif_receive_skb+0x48/0x250 net/core/dev.c:4303 [<ffffffff8241fc75>] tun_get_user+0xbd5/0x28a0 drivers/net/tun.c:1308 [<ffffffff82421b5a>] tun_chr_write_iter+0xda/0x190 drivers/net/tun.c:1332 [< inline >] new_sync_write fs/read_write.c:499 [<ffffffff8151bd44>] __vfs_write+0x334/0x570 fs/read_write.c:512 [<ffffffff8151f85b>] vfs_write+0x17b/0x500 fs/read_write.c:560 [< inline >] SYSC_write fs/read_write.c:607 [<ffffffff81523184>] SyS_write+0xd4/0x1a0 fs/read_write.c:599 [<ffffffff83fc02c1>] entry_SYSCALL_64_fastpath+0x1f/0xc2 It turns out DCCP calls __sk_receive_skb(), and this broke when lookups no longer took a reference on listeners. Fix this issue by adding a @refcounted parameter to __sk_receive_skb(), so that sock_put() is used only when needed. Fixes: 3b24d854cb35 ("tcp/dccp: do not touch listener sk_refcnt under synflood") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: Andrey Konovalov <andreyknvl@google.com> Tested-by: Andrey Konovalov <andreyknvl@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-03 00:14:41 +00:00
const int nested, unsigned int trim_cap, bool refcounted)
[NET]: deinline 200+ byte inlines in sock.h Sizes in bytes (allyesconfig, i386) and files where those inlines are used: 238 sock_queue_rcv_skb 2.6.16/net/x25/x25_in.o 238 sock_queue_rcv_skb 2.6.16/net/rose/rose_in.o 238 sock_queue_rcv_skb 2.6.16/net/packet/af_packet.o 238 sock_queue_rcv_skb 2.6.16/net/netrom/nr_in.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_sap.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_conn.o 238 sock_queue_rcv_skb 2.6.16/net/irda/af_irda.o 238 sock_queue_rcv_skb 2.6.16/net/ipx/af_ipx.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/ipmr.o 238 sock_queue_rcv_skb 2.6.16/net/econet/econet.o 238 sock_queue_rcv_skb 2.6.16/net/econet/af_econet.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/sco.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/l2cap.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/hci_sock.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/ax25_in.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/af_ax25.o 238 sock_queue_rcv_skb 2.6.16/net/appletalk/ddp.o 238 sock_queue_rcv_skb 2.6.16/drivers/net/pppoe.o 276 sk_receive_skb 2.6.16/net/decnet/dn_nsp_in.o 276 sk_receive_skb 2.6.16/net/dccp/ipv6.o 276 sk_receive_skb 2.6.16/net/dccp/ipv4.o 276 sk_receive_skb 2.6.16/net/dccp/dccp_ipv6.o 276 sk_receive_skb 2.6.16/drivers/net/pppoe.o 209 sk_dst_check 2.6.16/net/ipv6/ip6_output.o 209 sk_dst_check 2.6.16/net/ipv4/udp.o 209 sk_dst_check 2.6.16/net/decnet/dn_nsp_out.o Large inlines with multiple callers: Size Uses Wasted Name and definition ===== ==== ====== ================================================ 238 21 4360 sock_queue_rcv_skb include/net/sock.h 109 10 801 sock_recv_timestamp include/net/sock.h 276 4 768 sk_receive_skb include/net/sock.h 94 8 518 __sk_dst_check include/net/sock.h 209 3 378 sk_dst_check include/net/sock.h 131 4 333 sk_setup_caps include/net/sock.h 152 2 132 sk_stream_alloc_pskb include/net/sock.h 125 2 105 sk_stream_writequeue_purge include/net/sock.h Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-28 09:08:21 +00:00
{
int rc = NET_RX_SUCCESS;
if (sk_filter_trim_cap(sk, skb, trim_cap))
[NET]: deinline 200+ byte inlines in sock.h Sizes in bytes (allyesconfig, i386) and files where those inlines are used: 238 sock_queue_rcv_skb 2.6.16/net/x25/x25_in.o 238 sock_queue_rcv_skb 2.6.16/net/rose/rose_in.o 238 sock_queue_rcv_skb 2.6.16/net/packet/af_packet.o 238 sock_queue_rcv_skb 2.6.16/net/netrom/nr_in.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_sap.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_conn.o 238 sock_queue_rcv_skb 2.6.16/net/irda/af_irda.o 238 sock_queue_rcv_skb 2.6.16/net/ipx/af_ipx.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/ipmr.o 238 sock_queue_rcv_skb 2.6.16/net/econet/econet.o 238 sock_queue_rcv_skb 2.6.16/net/econet/af_econet.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/sco.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/l2cap.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/hci_sock.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/ax25_in.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/af_ax25.o 238 sock_queue_rcv_skb 2.6.16/net/appletalk/ddp.o 238 sock_queue_rcv_skb 2.6.16/drivers/net/pppoe.o 276 sk_receive_skb 2.6.16/net/decnet/dn_nsp_in.o 276 sk_receive_skb 2.6.16/net/dccp/ipv6.o 276 sk_receive_skb 2.6.16/net/dccp/ipv4.o 276 sk_receive_skb 2.6.16/net/dccp/dccp_ipv6.o 276 sk_receive_skb 2.6.16/drivers/net/pppoe.o 209 sk_dst_check 2.6.16/net/ipv6/ip6_output.o 209 sk_dst_check 2.6.16/net/ipv4/udp.o 209 sk_dst_check 2.6.16/net/decnet/dn_nsp_out.o Large inlines with multiple callers: Size Uses Wasted Name and definition ===== ==== ====== ================================================ 238 21 4360 sock_queue_rcv_skb include/net/sock.h 109 10 801 sock_recv_timestamp include/net/sock.h 276 4 768 sk_receive_skb include/net/sock.h 94 8 518 __sk_dst_check include/net/sock.h 209 3 378 sk_dst_check include/net/sock.h 131 4 333 sk_setup_caps include/net/sock.h 152 2 132 sk_stream_alloc_pskb include/net/sock.h 125 2 105 sk_stream_writequeue_purge include/net/sock.h Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-28 09:08:21 +00:00
goto discard_and_relse;
skb->dev = NULL;
if (sk_rcvqueues_full(sk, sk->sk_rcvbuf)) {
atomic_inc(&sk->sk_drops);
goto discard_and_relse;
}
if (nested)
bh_lock_sock_nested(sk);
else
bh_lock_sock(sk);
if (!sock_owned_by_user(sk)) {
/*
* trylock + unlock semantics:
*/
mutex_acquire(&sk->sk_lock.dep_map, 0, 1, _RET_IP_);
rc = sk_backlog_rcv(sk, skb);
2019-09-19 16:09:40 +00:00
mutex_release(&sk->sk_lock.dep_map, _RET_IP_);
net: silence KCSAN warnings around sk_add_backlog() calls sk_add_backlog() callers usually read sk->sk_rcvbuf without owning the socket lock. This means sk_rcvbuf value can be changed by other cpus, and KCSAN complains. Add READ_ONCE() annotations to document the lockless nature of these reads. Note that writes over sk_rcvbuf should also use WRITE_ONCE(), but this will be done in separate patches to ease stable backports (if we decide this is relevant for stable trees). BUG: KCSAN: data-race in tcp_add_backlog / tcp_recvmsg write to 0xffff88812ab369f8 of 8 bytes by interrupt on cpu 1: __sk_add_backlog include/net/sock.h:902 [inline] sk_add_backlog include/net/sock.h:933 [inline] tcp_add_backlog+0x45a/0xcc0 net/ipv4/tcp_ipv4.c:1737 tcp_v4_rcv+0x1aba/0x1bf0 net/ipv4/tcp_ipv4.c:1925 ip_protocol_deliver_rcu+0x51/0x470 net/ipv4/ip_input.c:204 ip_local_deliver_finish+0x110/0x140 net/ipv4/ip_input.c:231 NF_HOOK include/linux/netfilter.h:305 [inline] NF_HOOK include/linux/netfilter.h:299 [inline] ip_local_deliver+0x133/0x210 net/ipv4/ip_input.c:252 dst_input include/net/dst.h:442 [inline] ip_rcv_finish+0x121/0x160 net/ipv4/ip_input.c:413 NF_HOOK include/linux/netfilter.h:305 [inline] NF_HOOK include/linux/netfilter.h:299 [inline] ip_rcv+0x18f/0x1a0 net/ipv4/ip_input.c:523 __netif_receive_skb_one_core+0xa7/0xe0 net/core/dev.c:5004 __netif_receive_skb+0x37/0xf0 net/core/dev.c:5118 netif_receive_skb_internal+0x59/0x190 net/core/dev.c:5208 napi_skb_finish net/core/dev.c:5671 [inline] napi_gro_receive+0x28f/0x330 net/core/dev.c:5704 receive_buf+0x284/0x30b0 drivers/net/virtio_net.c:1061 virtnet_receive drivers/net/virtio_net.c:1323 [inline] virtnet_poll+0x436/0x7d0 drivers/net/virtio_net.c:1428 napi_poll net/core/dev.c:6352 [inline] net_rx_action+0x3ae/0xa50 net/core/dev.c:6418 read to 0xffff88812ab369f8 of 8 bytes by task 7271 on cpu 0: tcp_recvmsg+0x470/0x1a30 net/ipv4/tcp.c:2047 inet_recvmsg+0xbb/0x250 net/ipv4/af_inet.c:838 sock_recvmsg_nosec net/socket.c:871 [inline] sock_recvmsg net/socket.c:889 [inline] sock_recvmsg+0x92/0xb0 net/socket.c:885 sock_read_iter+0x15f/0x1e0 net/socket.c:967 call_read_iter include/linux/fs.h:1864 [inline] new_sync_read+0x389/0x4f0 fs/read_write.c:414 __vfs_read+0xb1/0xc0 fs/read_write.c:427 vfs_read fs/read_write.c:461 [inline] vfs_read+0x143/0x2c0 fs/read_write.c:446 ksys_read+0xd5/0x1b0 fs/read_write.c:587 __do_sys_read fs/read_write.c:597 [inline] __se_sys_read fs/read_write.c:595 [inline] __x64_sys_read+0x4c/0x60 fs/read_write.c:595 do_syscall_64+0xcf/0x2f0 arch/x86/entry/common.c:296 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 7271 Comm: syz-fuzzer Not tainted 5.3.0+ #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
2019-10-09 22:21:13 +00:00
} else if (sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf))) {
net: add limit for socket backlog We got system OOM while running some UDP netperf testing on the loopback device. The case is multiple senders sent stream UDP packets to a single receiver via loopback on local host. Of course, the receiver is not able to handle all the packets in time. But we surprisingly found that these packets were not discarded due to the receiver's sk->sk_rcvbuf limit. Instead, they are kept queuing to sk->sk_backlog and finally ate up all the memory. We believe this is a secure hole that a none privileged user can crash the system. The root cause for this problem is, when the receiver is doing __release_sock() (i.e. after userspace recv, kernel udp_recvmsg -> skb_free_datagram_locked -> release_sock), it moves skbs from backlog to sk_receive_queue with the softirq enabled. In the above case, multiple busy senders will almost make it an endless loop. The skbs in the backlog end up eat all the system memory. The issue is not only for UDP. Any protocols using socket backlog is potentially affected. The patch adds limit for socket backlog so that the backlog size cannot be expanded endlessly. Reported-by: Alex Shi <alex.shi@intel.com> Cc: David Miller <davem@davemloft.net> Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Cc: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru Cc: "Pekka Savola (ipv6)" <pekkas@netcore.fi> Cc: Patrick McHardy <kaber@trash.net> Cc: Vlad Yasevich <vladislav.yasevich@hp.com> Cc: Sridhar Samudrala <sri@us.ibm.com> Cc: Jon Maloy <jon.maloy@ericsson.com> Cc: Allan Stephens <allan.stephens@windriver.com> Cc: Andrew Hendry <andrew.hendry@gmail.com> Signed-off-by: Zhu Yi <yi.zhu@intel.com> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Acked-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-03-04 18:01:40 +00:00
bh_unlock_sock(sk);
atomic_inc(&sk->sk_drops);
goto discard_and_relse;
}
[NET]: deinline 200+ byte inlines in sock.h Sizes in bytes (allyesconfig, i386) and files where those inlines are used: 238 sock_queue_rcv_skb 2.6.16/net/x25/x25_in.o 238 sock_queue_rcv_skb 2.6.16/net/rose/rose_in.o 238 sock_queue_rcv_skb 2.6.16/net/packet/af_packet.o 238 sock_queue_rcv_skb 2.6.16/net/netrom/nr_in.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_sap.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_conn.o 238 sock_queue_rcv_skb 2.6.16/net/irda/af_irda.o 238 sock_queue_rcv_skb 2.6.16/net/ipx/af_ipx.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/ipmr.o 238 sock_queue_rcv_skb 2.6.16/net/econet/econet.o 238 sock_queue_rcv_skb 2.6.16/net/econet/af_econet.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/sco.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/l2cap.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/hci_sock.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/ax25_in.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/af_ax25.o 238 sock_queue_rcv_skb 2.6.16/net/appletalk/ddp.o 238 sock_queue_rcv_skb 2.6.16/drivers/net/pppoe.o 276 sk_receive_skb 2.6.16/net/decnet/dn_nsp_in.o 276 sk_receive_skb 2.6.16/net/dccp/ipv6.o 276 sk_receive_skb 2.6.16/net/dccp/ipv4.o 276 sk_receive_skb 2.6.16/net/dccp/dccp_ipv6.o 276 sk_receive_skb 2.6.16/drivers/net/pppoe.o 209 sk_dst_check 2.6.16/net/ipv6/ip6_output.o 209 sk_dst_check 2.6.16/net/ipv4/udp.o 209 sk_dst_check 2.6.16/net/decnet/dn_nsp_out.o Large inlines with multiple callers: Size Uses Wasted Name and definition ===== ==== ====== ================================================ 238 21 4360 sock_queue_rcv_skb include/net/sock.h 109 10 801 sock_recv_timestamp include/net/sock.h 276 4 768 sk_receive_skb include/net/sock.h 94 8 518 __sk_dst_check include/net/sock.h 209 3 378 sk_dst_check include/net/sock.h 131 4 333 sk_setup_caps include/net/sock.h 152 2 132 sk_stream_alloc_pskb include/net/sock.h 125 2 105 sk_stream_writequeue_purge include/net/sock.h Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-28 09:08:21 +00:00
bh_unlock_sock(sk);
out:
dccp: do not release listeners too soon Andrey Konovalov reported following error while fuzzing with syzkaller : IPv4: Attempt to release alive inet socket ffff880068e98940 kasan: CONFIG_KASAN_INLINE enabled kasan: GPF could be caused by NULL-ptr deref or user memory access general protection fault: 0000 [#1] SMP KASAN Modules linked in: CPU: 1 PID: 3905 Comm: a.out Not tainted 4.9.0-rc3+ #333 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 task: ffff88006b9e0000 task.stack: ffff880068770000 RIP: 0010:[<ffffffff819ead5f>] [<ffffffff819ead5f>] selinux_socket_sock_rcv_skb+0xff/0x6a0 security/selinux/hooks.c:4639 RSP: 0018:ffff8800687771c8 EFLAGS: 00010202 RAX: ffff88006b9e0000 RBX: 1ffff1000d0eee3f RCX: 1ffff1000d1d312a RDX: 1ffff1000d1d31a6 RSI: dffffc0000000000 RDI: 0000000000000010 RBP: ffff880068777360 R08: 0000000000000000 R09: 0000000000000002 R10: dffffc0000000000 R11: 0000000000000006 R12: ffff880068e98940 R13: 0000000000000002 R14: ffff880068777338 R15: 0000000000000000 FS: 00007f00ff760700(0000) GS:ffff88006cd00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020008000 CR3: 000000006a308000 CR4: 00000000000006e0 Stack: ffff8800687771e0 ffffffff812508a5 ffff8800686f3168 0000000000000007 ffff88006ac8cdfc ffff8800665ea500 0000000041b58ab3 ffffffff847b5480 ffffffff819eac60 ffff88006b9e0860 ffff88006b9e0868 ffff88006b9e07f0 Call Trace: [<ffffffff819c8dd5>] security_sock_rcv_skb+0x75/0xb0 security/security.c:1317 [<ffffffff82c2a9e7>] sk_filter_trim_cap+0x67/0x10e0 net/core/filter.c:81 [<ffffffff82b81e60>] __sk_receive_skb+0x30/0xa00 net/core/sock.c:460 [<ffffffff838bbf12>] dccp_v4_rcv+0xdb2/0x1910 net/dccp/ipv4.c:873 [<ffffffff83069d22>] ip_local_deliver_finish+0x332/0xad0 net/ipv4/ip_input.c:216 [< inline >] NF_HOOK_THRESH ./include/linux/netfilter.h:232 [< inline >] NF_HOOK ./include/linux/netfilter.h:255 [<ffffffff8306abd2>] ip_local_deliver+0x1c2/0x4b0 net/ipv4/ip_input.c:257 [< inline >] dst_input ./include/net/dst.h:507 [<ffffffff83068500>] ip_rcv_finish+0x750/0x1c40 net/ipv4/ip_input.c:396 [< inline >] NF_HOOK_THRESH ./include/linux/netfilter.h:232 [< inline >] NF_HOOK ./include/linux/netfilter.h:255 [<ffffffff8306b82f>] ip_rcv+0x96f/0x12f0 net/ipv4/ip_input.c:487 [<ffffffff82bd9fb7>] __netif_receive_skb_core+0x1897/0x2a50 net/core/dev.c:4213 [<ffffffff82bdb19a>] __netif_receive_skb+0x2a/0x170 net/core/dev.c:4251 [<ffffffff82bdb493>] netif_receive_skb_internal+0x1b3/0x390 net/core/dev.c:4279 [<ffffffff82bdb6b8>] netif_receive_skb+0x48/0x250 net/core/dev.c:4303 [<ffffffff8241fc75>] tun_get_user+0xbd5/0x28a0 drivers/net/tun.c:1308 [<ffffffff82421b5a>] tun_chr_write_iter+0xda/0x190 drivers/net/tun.c:1332 [< inline >] new_sync_write fs/read_write.c:499 [<ffffffff8151bd44>] __vfs_write+0x334/0x570 fs/read_write.c:512 [<ffffffff8151f85b>] vfs_write+0x17b/0x500 fs/read_write.c:560 [< inline >] SYSC_write fs/read_write.c:607 [<ffffffff81523184>] SyS_write+0xd4/0x1a0 fs/read_write.c:599 [<ffffffff83fc02c1>] entry_SYSCALL_64_fastpath+0x1f/0xc2 It turns out DCCP calls __sk_receive_skb(), and this broke when lookups no longer took a reference on listeners. Fix this issue by adding a @refcounted parameter to __sk_receive_skb(), so that sock_put() is used only when needed. Fixes: 3b24d854cb35 ("tcp/dccp: do not touch listener sk_refcnt under synflood") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: Andrey Konovalov <andreyknvl@google.com> Tested-by: Andrey Konovalov <andreyknvl@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-03 00:14:41 +00:00
if (refcounted)
sock_put(sk);
[NET]: deinline 200+ byte inlines in sock.h Sizes in bytes (allyesconfig, i386) and files where those inlines are used: 238 sock_queue_rcv_skb 2.6.16/net/x25/x25_in.o 238 sock_queue_rcv_skb 2.6.16/net/rose/rose_in.o 238 sock_queue_rcv_skb 2.6.16/net/packet/af_packet.o 238 sock_queue_rcv_skb 2.6.16/net/netrom/nr_in.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_sap.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_conn.o 238 sock_queue_rcv_skb 2.6.16/net/irda/af_irda.o 238 sock_queue_rcv_skb 2.6.16/net/ipx/af_ipx.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/ipmr.o 238 sock_queue_rcv_skb 2.6.16/net/econet/econet.o 238 sock_queue_rcv_skb 2.6.16/net/econet/af_econet.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/sco.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/l2cap.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/hci_sock.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/ax25_in.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/af_ax25.o 238 sock_queue_rcv_skb 2.6.16/net/appletalk/ddp.o 238 sock_queue_rcv_skb 2.6.16/drivers/net/pppoe.o 276 sk_receive_skb 2.6.16/net/decnet/dn_nsp_in.o 276 sk_receive_skb 2.6.16/net/dccp/ipv6.o 276 sk_receive_skb 2.6.16/net/dccp/ipv4.o 276 sk_receive_skb 2.6.16/net/dccp/dccp_ipv6.o 276 sk_receive_skb 2.6.16/drivers/net/pppoe.o 209 sk_dst_check 2.6.16/net/ipv6/ip6_output.o 209 sk_dst_check 2.6.16/net/ipv4/udp.o 209 sk_dst_check 2.6.16/net/decnet/dn_nsp_out.o Large inlines with multiple callers: Size Uses Wasted Name and definition ===== ==== ====== ================================================ 238 21 4360 sock_queue_rcv_skb include/net/sock.h 109 10 801 sock_recv_timestamp include/net/sock.h 276 4 768 sk_receive_skb include/net/sock.h 94 8 518 __sk_dst_check include/net/sock.h 209 3 378 sk_dst_check include/net/sock.h 131 4 333 sk_setup_caps include/net/sock.h 152 2 132 sk_stream_alloc_pskb include/net/sock.h 125 2 105 sk_stream_writequeue_purge include/net/sock.h Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-28 09:08:21 +00:00
return rc;
discard_and_relse:
kfree_skb(skb);
goto out;
}
EXPORT_SYMBOL(__sk_receive_skb);
[NET]: deinline 200+ byte inlines in sock.h Sizes in bytes (allyesconfig, i386) and files where those inlines are used: 238 sock_queue_rcv_skb 2.6.16/net/x25/x25_in.o 238 sock_queue_rcv_skb 2.6.16/net/rose/rose_in.o 238 sock_queue_rcv_skb 2.6.16/net/packet/af_packet.o 238 sock_queue_rcv_skb 2.6.16/net/netrom/nr_in.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_sap.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_conn.o 238 sock_queue_rcv_skb 2.6.16/net/irda/af_irda.o 238 sock_queue_rcv_skb 2.6.16/net/ipx/af_ipx.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/ipmr.o 238 sock_queue_rcv_skb 2.6.16/net/econet/econet.o 238 sock_queue_rcv_skb 2.6.16/net/econet/af_econet.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/sco.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/l2cap.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/hci_sock.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/ax25_in.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/af_ax25.o 238 sock_queue_rcv_skb 2.6.16/net/appletalk/ddp.o 238 sock_queue_rcv_skb 2.6.16/drivers/net/pppoe.o 276 sk_receive_skb 2.6.16/net/decnet/dn_nsp_in.o 276 sk_receive_skb 2.6.16/net/dccp/ipv6.o 276 sk_receive_skb 2.6.16/net/dccp/ipv4.o 276 sk_receive_skb 2.6.16/net/dccp/dccp_ipv6.o 276 sk_receive_skb 2.6.16/drivers/net/pppoe.o 209 sk_dst_check 2.6.16/net/ipv6/ip6_output.o 209 sk_dst_check 2.6.16/net/ipv4/udp.o 209 sk_dst_check 2.6.16/net/decnet/dn_nsp_out.o Large inlines with multiple callers: Size Uses Wasted Name and definition ===== ==== ====== ================================================ 238 21 4360 sock_queue_rcv_skb include/net/sock.h 109 10 801 sock_recv_timestamp include/net/sock.h 276 4 768 sk_receive_skb include/net/sock.h 94 8 518 __sk_dst_check include/net/sock.h 209 3 378 sk_dst_check include/net/sock.h 131 4 333 sk_setup_caps include/net/sock.h 152 2 132 sk_stream_alloc_pskb include/net/sock.h 125 2 105 sk_stream_writequeue_purge include/net/sock.h Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-28 09:08:21 +00:00
INDIRECT_CALLABLE_DECLARE(struct dst_entry *ip6_dst_check(struct dst_entry *,
u32));
INDIRECT_CALLABLE_DECLARE(struct dst_entry *ipv4_dst_check(struct dst_entry *,
u32));
[NET]: deinline 200+ byte inlines in sock.h Sizes in bytes (allyesconfig, i386) and files where those inlines are used: 238 sock_queue_rcv_skb 2.6.16/net/x25/x25_in.o 238 sock_queue_rcv_skb 2.6.16/net/rose/rose_in.o 238 sock_queue_rcv_skb 2.6.16/net/packet/af_packet.o 238 sock_queue_rcv_skb 2.6.16/net/netrom/nr_in.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_sap.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_conn.o 238 sock_queue_rcv_skb 2.6.16/net/irda/af_irda.o 238 sock_queue_rcv_skb 2.6.16/net/ipx/af_ipx.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/ipmr.o 238 sock_queue_rcv_skb 2.6.16/net/econet/econet.o 238 sock_queue_rcv_skb 2.6.16/net/econet/af_econet.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/sco.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/l2cap.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/hci_sock.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/ax25_in.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/af_ax25.o 238 sock_queue_rcv_skb 2.6.16/net/appletalk/ddp.o 238 sock_queue_rcv_skb 2.6.16/drivers/net/pppoe.o 276 sk_receive_skb 2.6.16/net/decnet/dn_nsp_in.o 276 sk_receive_skb 2.6.16/net/dccp/ipv6.o 276 sk_receive_skb 2.6.16/net/dccp/ipv4.o 276 sk_receive_skb 2.6.16/net/dccp/dccp_ipv6.o 276 sk_receive_skb 2.6.16/drivers/net/pppoe.o 209 sk_dst_check 2.6.16/net/ipv6/ip6_output.o 209 sk_dst_check 2.6.16/net/ipv4/udp.o 209 sk_dst_check 2.6.16/net/decnet/dn_nsp_out.o Large inlines with multiple callers: Size Uses Wasted Name and definition ===== ==== ====== ================================================ 238 21 4360 sock_queue_rcv_skb include/net/sock.h 109 10 801 sock_recv_timestamp include/net/sock.h 276 4 768 sk_receive_skb include/net/sock.h 94 8 518 __sk_dst_check include/net/sock.h 209 3 378 sk_dst_check include/net/sock.h 131 4 333 sk_setup_caps include/net/sock.h 152 2 132 sk_stream_alloc_pskb include/net/sock.h 125 2 105 sk_stream_writequeue_purge include/net/sock.h Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-28 09:08:21 +00:00
struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie)
{
struct dst_entry *dst = __sk_dst_get(sk);
[NET]: deinline 200+ byte inlines in sock.h Sizes in bytes (allyesconfig, i386) and files where those inlines are used: 238 sock_queue_rcv_skb 2.6.16/net/x25/x25_in.o 238 sock_queue_rcv_skb 2.6.16/net/rose/rose_in.o 238 sock_queue_rcv_skb 2.6.16/net/packet/af_packet.o 238 sock_queue_rcv_skb 2.6.16/net/netrom/nr_in.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_sap.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_conn.o 238 sock_queue_rcv_skb 2.6.16/net/irda/af_irda.o 238 sock_queue_rcv_skb 2.6.16/net/ipx/af_ipx.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/ipmr.o 238 sock_queue_rcv_skb 2.6.16/net/econet/econet.o 238 sock_queue_rcv_skb 2.6.16/net/econet/af_econet.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/sco.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/l2cap.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/hci_sock.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/ax25_in.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/af_ax25.o 238 sock_queue_rcv_skb 2.6.16/net/appletalk/ddp.o 238 sock_queue_rcv_skb 2.6.16/drivers/net/pppoe.o 276 sk_receive_skb 2.6.16/net/decnet/dn_nsp_in.o 276 sk_receive_skb 2.6.16/net/dccp/ipv6.o 276 sk_receive_skb 2.6.16/net/dccp/ipv4.o 276 sk_receive_skb 2.6.16/net/dccp/dccp_ipv6.o 276 sk_receive_skb 2.6.16/drivers/net/pppoe.o 209 sk_dst_check 2.6.16/net/ipv6/ip6_output.o 209 sk_dst_check 2.6.16/net/ipv4/udp.o 209 sk_dst_check 2.6.16/net/decnet/dn_nsp_out.o Large inlines with multiple callers: Size Uses Wasted Name and definition ===== ==== ====== ================================================ 238 21 4360 sock_queue_rcv_skb include/net/sock.h 109 10 801 sock_recv_timestamp include/net/sock.h 276 4 768 sk_receive_skb include/net/sock.h 94 8 518 __sk_dst_check include/net/sock.h 209 3 378 sk_dst_check include/net/sock.h 131 4 333 sk_setup_caps include/net/sock.h 152 2 132 sk_stream_alloc_pskb include/net/sock.h 125 2 105 sk_stream_writequeue_purge include/net/sock.h Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-28 09:08:21 +00:00
if (dst && dst->obsolete &&
INDIRECT_CALL_INET(dst->ops->check, ip6_dst_check, ipv4_dst_check,
dst, cookie) == NULL) {
sk_tx_queue_clear(sk);
sk->sk_dst_pending_confirm = 0;
RCU_INIT_POINTER(sk->sk_dst_cache, NULL);
[NET]: deinline 200+ byte inlines in sock.h Sizes in bytes (allyesconfig, i386) and files where those inlines are used: 238 sock_queue_rcv_skb 2.6.16/net/x25/x25_in.o 238 sock_queue_rcv_skb 2.6.16/net/rose/rose_in.o 238 sock_queue_rcv_skb 2.6.16/net/packet/af_packet.o 238 sock_queue_rcv_skb 2.6.16/net/netrom/nr_in.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_sap.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_conn.o 238 sock_queue_rcv_skb 2.6.16/net/irda/af_irda.o 238 sock_queue_rcv_skb 2.6.16/net/ipx/af_ipx.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/ipmr.o 238 sock_queue_rcv_skb 2.6.16/net/econet/econet.o 238 sock_queue_rcv_skb 2.6.16/net/econet/af_econet.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/sco.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/l2cap.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/hci_sock.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/ax25_in.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/af_ax25.o 238 sock_queue_rcv_skb 2.6.16/net/appletalk/ddp.o 238 sock_queue_rcv_skb 2.6.16/drivers/net/pppoe.o 276 sk_receive_skb 2.6.16/net/decnet/dn_nsp_in.o 276 sk_receive_skb 2.6.16/net/dccp/ipv6.o 276 sk_receive_skb 2.6.16/net/dccp/ipv4.o 276 sk_receive_skb 2.6.16/net/dccp/dccp_ipv6.o 276 sk_receive_skb 2.6.16/drivers/net/pppoe.o 209 sk_dst_check 2.6.16/net/ipv6/ip6_output.o 209 sk_dst_check 2.6.16/net/ipv4/udp.o 209 sk_dst_check 2.6.16/net/decnet/dn_nsp_out.o Large inlines with multiple callers: Size Uses Wasted Name and definition ===== ==== ====== ================================================ 238 21 4360 sock_queue_rcv_skb include/net/sock.h 109 10 801 sock_recv_timestamp include/net/sock.h 276 4 768 sk_receive_skb include/net/sock.h 94 8 518 __sk_dst_check include/net/sock.h 209 3 378 sk_dst_check include/net/sock.h 131 4 333 sk_setup_caps include/net/sock.h 152 2 132 sk_stream_alloc_pskb include/net/sock.h 125 2 105 sk_stream_writequeue_purge include/net/sock.h Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-28 09:08:21 +00:00
dst_release(dst);
return NULL;
}
return dst;
}
EXPORT_SYMBOL(__sk_dst_check);
struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie)
{
struct dst_entry *dst = sk_dst_get(sk);
if (dst && dst->obsolete &&
INDIRECT_CALL_INET(dst->ops->check, ip6_dst_check, ipv4_dst_check,
dst, cookie) == NULL) {
[NET]: deinline 200+ byte inlines in sock.h Sizes in bytes (allyesconfig, i386) and files where those inlines are used: 238 sock_queue_rcv_skb 2.6.16/net/x25/x25_in.o 238 sock_queue_rcv_skb 2.6.16/net/rose/rose_in.o 238 sock_queue_rcv_skb 2.6.16/net/packet/af_packet.o 238 sock_queue_rcv_skb 2.6.16/net/netrom/nr_in.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_sap.o 238 sock_queue_rcv_skb 2.6.16/net/llc/llc_conn.o 238 sock_queue_rcv_skb 2.6.16/net/irda/af_irda.o 238 sock_queue_rcv_skb 2.6.16/net/ipx/af_ipx.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv6/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/udp.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/raw.o 238 sock_queue_rcv_skb 2.6.16/net/ipv4/ipmr.o 238 sock_queue_rcv_skb 2.6.16/net/econet/econet.o 238 sock_queue_rcv_skb 2.6.16/net/econet/af_econet.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/sco.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/l2cap.o 238 sock_queue_rcv_skb 2.6.16/net/bluetooth/hci_sock.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/ax25_in.o 238 sock_queue_rcv_skb 2.6.16/net/ax25/af_ax25.o 238 sock_queue_rcv_skb 2.6.16/net/appletalk/ddp.o 238 sock_queue_rcv_skb 2.6.16/drivers/net/pppoe.o 276 sk_receive_skb 2.6.16/net/decnet/dn_nsp_in.o 276 sk_receive_skb 2.6.16/net/dccp/ipv6.o 276 sk_receive_skb 2.6.16/net/dccp/ipv4.o 276 sk_receive_skb 2.6.16/net/dccp/dccp_ipv6.o 276 sk_receive_skb 2.6.16/drivers/net/pppoe.o 209 sk_dst_check 2.6.16/net/ipv6/ip6_output.o 209 sk_dst_check 2.6.16/net/ipv4/udp.o 209 sk_dst_check 2.6.16/net/decnet/dn_nsp_out.o Large inlines with multiple callers: Size Uses Wasted Name and definition ===== ==== ====== ================================================ 238 21 4360 sock_queue_rcv_skb include/net/sock.h 109 10 801 sock_recv_timestamp include/net/sock.h 276 4 768 sk_receive_skb include/net/sock.h 94 8 518 __sk_dst_check include/net/sock.h 209 3 378 sk_dst_check include/net/sock.h 131 4 333 sk_setup_caps include/net/sock.h 152 2 132 sk_stream_alloc_pskb include/net/sock.h 125 2 105 sk_stream_writequeue_purge include/net/sock.h Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-28 09:08:21 +00:00
sk_dst_reset(sk);
dst_release(dst);
return NULL;
}
return dst;
}
EXPORT_SYMBOL(sk_dst_check);
static int sock_bindtoindex_locked(struct sock *sk, int ifindex)
{
int ret = -ENOPROTOOPT;
#ifdef CONFIG_NETDEVICES
struct net *net = sock_net(sk);
/* Sorry... */
ret = -EPERM;
net: core: enable SO_BINDTODEVICE for non-root users Currently, SO_BINDTODEVICE requires CAP_NET_RAW. This change allows a non-root user to bind a socket to an interface if it is not already bound. This is useful to allow an application to bind itself to a specific VRF for outgoing or incoming connections. Currently, an application wanting to manage connections through several VRF need to be privileged. Previously, IP_UNICAST_IF and IPV6_UNICAST_IF were added for Wine (76e21053b5bf3 and c4062dfc425e9) specifically for use by non-root processes. However, they are restricted to sendmsg() and not usable with TCP. Allowing SO_BINDTODEVICE would allow TCP clients to get the same privilege. As for TCP servers, outside the VRF use case, SO_BINDTODEVICE would only further restrict connections a server could accept. When an application is restricted to a VRF (with `ip vrf exec`), the socket is bound to an interface at creation and therefore, a non-privileged call to SO_BINDTODEVICE to escape the VRF fails. When an application bound a socket to SO_BINDTODEVICE and transmit it to a non-privileged process through a Unix socket, a tentative to change the bound device also fails. Before: >>> import socket >>> s=socket.socket(socket.AF_INET, socket.SOCK_STREAM) >>> s.setsockopt(socket.SOL_SOCKET, socket.SO_BINDTODEVICE, b"dummy0") Traceback (most recent call last): File "<stdin>", line 1, in <module> PermissionError: [Errno 1] Operation not permitted After: >>> import socket >>> s=socket.socket(socket.AF_INET, socket.SOCK_STREAM) >>> s.setsockopt(socket.SOL_SOCKET, socket.SO_BINDTODEVICE, b"dummy0") >>> s.setsockopt(socket.SOL_SOCKET, socket.SO_BINDTODEVICE, b"dummy0") Traceback (most recent call last): File "<stdin>", line 1, in <module> PermissionError: [Errno 1] Operation not permitted Signed-off-by: Vincent Bernat <vincent@bernat.ch> Reviewed-by: David Ahern <dsahern@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-03-31 13:20:10 +00:00
if (sk->sk_bound_dev_if && !ns_capable(net->user_ns, CAP_NET_RAW))
goto out;
net: introduce SO_BINDTOIFINDEX sockopt This introduces a new generic SOL_SOCKET-level socket option called SO_BINDTOIFINDEX. It behaves similar to SO_BINDTODEVICE, but takes a network interface index as argument, rather than the network interface name. User-space often refers to network-interfaces via their index, but has to temporarily resolve it to a name for a call into SO_BINDTODEVICE. This might pose problems when the network-device is renamed asynchronously by other parts of the system. When this happens, the SO_BINDTODEVICE might either fail, or worse, it might bind to the wrong device. In most cases user-space only ever operates on devices which they either manage themselves, or otherwise have a guarantee that the device name will not change (e.g., devices that are UP cannot be renamed). However, particularly in libraries this guarantee is non-obvious and it would be nice if that race-condition would simply not exist. It would make it easier for those libraries to operate even in situations where the device-name might change under the hood. A real use-case that we recently hit is trying to start the network stack early in the initrd but make it survive into the real system. Existing distributions rename network-interfaces during the transition from initrd into the real system. This, obviously, cannot affect devices that are up and running (unless you also consider moving them between network-namespaces). However, the network manager now has to make sure its management engine for dormant devices will not run in parallel to these renames. Particularly, when you offload operations like DHCP into separate processes, these might setup their sockets early, and thus have to resolve the device-name possibly running into this race-condition. By avoiding a call to resolve the device-name, we no longer depend on the name and can run network setup of dormant devices in parallel to the transition off the initrd. The SO_BINDTOIFINDEX ioctl plugs this race. Reviewed-by: Tom Gundersen <teg@jklm.no> Signed-off-by: David Herrmann <dh.herrmann@gmail.com> Acked-by: Willem de Bruijn <willemb@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-01-15 13:42:14 +00:00
ret = -EINVAL;
if (ifindex < 0)
goto out;
sk->sk_bound_dev_if = ifindex;
if (sk->sk_prot->rehash)
sk->sk_prot->rehash(sk);
sk_dst_reset(sk);
ret = 0;
out:
#endif
return ret;
}
int sock_bindtoindex(struct sock *sk, int ifindex, bool lock_sk)
{
int ret;
if (lock_sk)
lock_sock(sk);
ret = sock_bindtoindex_locked(sk, ifindex);
if (lock_sk)
release_sock(sk);
return ret;
}
EXPORT_SYMBOL(sock_bindtoindex);
static int sock_setbindtodevice(struct sock *sk, sockptr_t optval, int optlen)
net: introduce SO_BINDTOIFINDEX sockopt This introduces a new generic SOL_SOCKET-level socket option called SO_BINDTOIFINDEX. It behaves similar to SO_BINDTODEVICE, but takes a network interface index as argument, rather than the network interface name. User-space often refers to network-interfaces via their index, but has to temporarily resolve it to a name for a call into SO_BINDTODEVICE. This might pose problems when the network-device is renamed asynchronously by other parts of the system. When this happens, the SO_BINDTODEVICE might either fail, or worse, it might bind to the wrong device. In most cases user-space only ever operates on devices which they either manage themselves, or otherwise have a guarantee that the device name will not change (e.g., devices that are UP cannot be renamed). However, particularly in libraries this guarantee is non-obvious and it would be nice if that race-condition would simply not exist. It would make it easier for those libraries to operate even in situations where the device-name might change under the hood. A real use-case that we recently hit is trying to start the network stack early in the initrd but make it survive into the real system. Existing distributions rename network-interfaces during the transition from initrd into the real system. This, obviously, cannot affect devices that are up and running (unless you also consider moving them between network-namespaces). However, the network manager now has to make sure its management engine for dormant devices will not run in parallel to these renames. Particularly, when you offload operations like DHCP into separate processes, these might setup their sockets early, and thus have to resolve the device-name possibly running into this race-condition. By avoiding a call to resolve the device-name, we no longer depend on the name and can run network setup of dormant devices in parallel to the transition off the initrd. The SO_BINDTOIFINDEX ioctl plugs this race. Reviewed-by: Tom Gundersen <teg@jklm.no> Signed-off-by: David Herrmann <dh.herrmann@gmail.com> Acked-by: Willem de Bruijn <willemb@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-01-15 13:42:14 +00:00
{
int ret = -ENOPROTOOPT;
#ifdef CONFIG_NETDEVICES
struct net *net = sock_net(sk);
char devname[IFNAMSIZ];
int index;
ret = -EINVAL;
if (optlen < 0)
goto out;
/* Bind this socket to a particular device like "eth0",
* as specified in the passed interface name. If the
* name is "" or the option length is zero the socket
* is not bound.
*/
if (optlen > IFNAMSIZ - 1)
optlen = IFNAMSIZ - 1;
memset(devname, 0, sizeof(devname));
ret = -EFAULT;
if (copy_from_sockptr(devname, optval, optlen))
goto out;
index = 0;
if (devname[0] != '\0') {
struct net_device *dev;
rcu_read_lock();
dev = dev_get_by_name_rcu(net, devname);
if (dev)
index = dev->ifindex;
rcu_read_unlock();
ret = -ENODEV;
if (!dev)
goto out;
}
return sock_bindtoindex(sk, index, true);
out:
#endif
return ret;
}
static int sock_getbindtodevice(struct sock *sk, char __user *optval,
int __user *optlen, int len)
{
int ret = -ENOPROTOOPT;
#ifdef CONFIG_NETDEVICES
struct net *net = sock_net(sk);
char devname[IFNAMSIZ];
if (sk->sk_bound_dev_if == 0) {
len = 0;
goto zero;
}
ret = -EINVAL;
if (len < IFNAMSIZ)
goto out;
ret = netdev_get_name(net, devname, sk->sk_bound_dev_if);
if (ret)
goto out;
len = strlen(devname) + 1;
ret = -EFAULT;
if (copy_to_user(optval, devname, len))
goto out;
zero:
ret = -EFAULT;
if (put_user(len, optlen))
goto out;
ret = 0;
out:
#endif
return ret;
}
bool sk_mc_loop(struct sock *sk)
{
if (dev_recursion_level())
return false;
if (!sk)
return true;
switch (sk->sk_family) {
case AF_INET:
return inet_sk(sk)->mc_loop;
#if IS_ENABLED(CONFIG_IPV6)
case AF_INET6:
return inet6_sk(sk)->mc_loop;
#endif
}
net: increment xmit_recursion level in dev_direct_xmit() Back in commit f60e5990d9c1 ("ipv6: protect skb->sk accesses from recursive dereference inside the stack") Hannes added code so that IPv6 stack would not trust skb->sk for typical cases where packet goes through 'standard' xmit path (__dev_queue_xmit()) Alas af_packet had a dev_direct_xmit() path that was not dealing yet with xmit_recursion level. Also change sk_mc_loop() to dump a stack once only. Without this patch, syzbot was able to trigger : [1] [ 153.567378] WARNING: CPU: 7 PID: 11273 at net/core/sock.c:721 sk_mc_loop+0x51/0x70 [ 153.567378] Modules linked in: nfnetlink ip6table_raw ip6table_filter iptable_raw iptable_nat nf_nat nf_conntrack nf_defrag_ipv4 nf_defrag_ipv6 iptable_filter macsec macvtap tap macvlan 8021q hsr wireguard libblake2s blake2s_x86_64 libblake2s_generic udp_tunnel ip6_udp_tunnel libchacha20poly1305 poly1305_x86_64 chacha_x86_64 libchacha curve25519_x86_64 libcurve25519_generic netdevsim batman_adv dummy team bridge stp llc w1_therm wire i2c_mux_pca954x i2c_mux cdc_acm ehci_pci ehci_hcd mlx4_en mlx4_ib ib_uverbs ib_core mlx4_core [ 153.567386] CPU: 7 PID: 11273 Comm: b159172088 Not tainted 5.8.0-smp-DEV #273 [ 153.567387] RIP: 0010:sk_mc_loop+0x51/0x70 [ 153.567388] Code: 66 83 f8 0a 75 24 0f b6 4f 12 b8 01 00 00 00 31 d2 d3 e0 a9 bf ef ff ff 74 07 48 8b 97 f0 02 00 00 0f b6 42 3a 83 e0 01 5d c3 <0f> 0b b8 01 00 00 00 5d c3 0f b6 87 18 03 00 00 5d c0 e8 04 83 e0 [ 153.567388] RSP: 0018:ffff95c69bb93990 EFLAGS: 00010212 [ 153.567388] RAX: 0000000000000011 RBX: ffff95c6e0ee3e00 RCX: 0000000000000007 [ 153.567389] RDX: ffff95c69ae50000 RSI: ffff95c6c30c3000 RDI: ffff95c6c30c3000 [ 153.567389] RBP: ffff95c69bb93990 R08: ffff95c69a77f000 R09: 0000000000000008 [ 153.567389] R10: 0000000000000040 R11: 00003e0e00026128 R12: ffff95c6c30c3000 [ 153.567390] R13: ffff95c6cc4fd500 R14: ffff95c6f84500c0 R15: ffff95c69aa13c00 [ 153.567390] FS: 00007fdc3a283700(0000) GS:ffff95c6ff9c0000(0000) knlGS:0000000000000000 [ 153.567390] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 153.567391] CR2: 00007ffee758e890 CR3: 0000001f9ba20003 CR4: 00000000001606e0 [ 153.567391] Call Trace: [ 153.567391] ip6_finish_output2+0x34e/0x550 [ 153.567391] __ip6_finish_output+0xe7/0x110 [ 153.567391] ip6_finish_output+0x2d/0xb0 [ 153.567392] ip6_output+0x77/0x120 [ 153.567392] ? __ip6_finish_output+0x110/0x110 [ 153.567392] ip6_local_out+0x3d/0x50 [ 153.567392] ipvlan_queue_xmit+0x56c/0x5e0 [ 153.567393] ? ksize+0x19/0x30 [ 153.567393] ipvlan_start_xmit+0x18/0x50 [ 153.567393] dev_direct_xmit+0xf3/0x1c0 [ 153.567393] packet_direct_xmit+0x69/0xa0 [ 153.567394] packet_sendmsg+0xbf0/0x19b0 [ 153.567394] ? plist_del+0x62/0xb0 [ 153.567394] sock_sendmsg+0x65/0x70 [ 153.567394] sock_write_iter+0x93/0xf0 [ 153.567394] new_sync_write+0x18e/0x1a0 [ 153.567395] __vfs_write+0x29/0x40 [ 153.567395] vfs_write+0xb9/0x1b0 [ 153.567395] ksys_write+0xb1/0xe0 [ 153.567395] __x64_sys_write+0x1a/0x20 [ 153.567395] do_syscall_64+0x43/0x70 [ 153.567396] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 153.567396] RIP: 0033:0x453549 [ 153.567396] Code: Bad RIP value. [ 153.567396] RSP: 002b:00007fdc3a282cc8 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 [ 153.567397] RAX: ffffffffffffffda RBX: 00000000004d32d0 RCX: 0000000000453549 [ 153.567397] RDX: 0000000000000020 RSI: 0000000020000300 RDI: 0000000000000003 [ 153.567398] RBP: 00000000004d32d8 R08: 0000000000000000 R09: 0000000000000000 [ 153.567398] R10: 0000000000000000 R11: 0000000000000246 R12: 00000000004d32dc [ 153.567398] R13: 00007ffee742260f R14: 00007fdc3a282dc0 R15: 00007fdc3a283700 [ 153.567399] ---[ end trace c1d5ae2b1059ec62 ]--- f60e5990d9c1 ("ipv6: protect skb->sk accesses from recursive dereference inside the stack") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-06-18 05:23:25 +00:00
WARN_ON_ONCE(1);
return true;
}
EXPORT_SYMBOL(sk_mc_loop);
void sock_set_reuseaddr(struct sock *sk)
{
lock_sock(sk);
sk->sk_reuse = SK_CAN_REUSE;
release_sock(sk);
}
EXPORT_SYMBOL(sock_set_reuseaddr);
void sock_set_reuseport(struct sock *sk)
{
lock_sock(sk);
sk->sk_reuseport = true;
release_sock(sk);
}
EXPORT_SYMBOL(sock_set_reuseport);
void sock_no_linger(struct sock *sk)
{
lock_sock(sk);
sk->sk_lingertime = 0;
sock_set_flag(sk, SOCK_LINGER);
release_sock(sk);
}
EXPORT_SYMBOL(sock_no_linger);
void sock_set_priority(struct sock *sk, u32 priority)
{
lock_sock(sk);
sk->sk_priority = priority;
release_sock(sk);
}
EXPORT_SYMBOL(sock_set_priority);
void sock_set_sndtimeo(struct sock *sk, s64 secs)
{
lock_sock(sk);
if (secs && secs < MAX_SCHEDULE_TIMEOUT / HZ - 1)
sk->sk_sndtimeo = secs * HZ;
else
sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT;
release_sock(sk);
}
EXPORT_SYMBOL(sock_set_sndtimeo);
static void __sock_set_timestamps(struct sock *sk, bool val, bool new, bool ns)
{
if (val) {
sock_valbool_flag(sk, SOCK_TSTAMP_NEW, new);
sock_valbool_flag(sk, SOCK_RCVTSTAMPNS, ns);
sock_set_flag(sk, SOCK_RCVTSTAMP);
sock_enable_timestamp(sk, SOCK_TIMESTAMP);
} else {
sock_reset_flag(sk, SOCK_RCVTSTAMP);
sock_reset_flag(sk, SOCK_RCVTSTAMPNS);
}
}
void sock_enable_timestamps(struct sock *sk)
{
lock_sock(sk);
__sock_set_timestamps(sk, true, false, true);
release_sock(sk);
}
EXPORT_SYMBOL(sock_enable_timestamps);
void sock_set_keepalive(struct sock *sk)
{
lock_sock(sk);
if (sk->sk_prot->keepalive)
sk->sk_prot->keepalive(sk, true);
sock_valbool_flag(sk, SOCK_KEEPOPEN, true);
release_sock(sk);
}
EXPORT_SYMBOL(sock_set_keepalive);
static void __sock_set_rcvbuf(struct sock *sk, int val)
{
/* Ensure val * 2 fits into an int, to prevent max_t() from treating it
* as a negative value.
*/
val = min_t(int, val, INT_MAX / 2);
sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
/* We double it on the way in to account for "struct sk_buff" etc.
* overhead. Applications assume that the SO_RCVBUF setting they make
* will allow that much actual data to be received on that socket.
*
* Applications are unaware that "struct sk_buff" and other overheads
* allocate from the receive buffer during socket buffer allocation.
*
* And after considering the possible alternatives, returning the value
* we actually used in getsockopt is the most desirable behavior.
*/
WRITE_ONCE(sk->sk_rcvbuf, max_t(int, val * 2, SOCK_MIN_RCVBUF));
}
void sock_set_rcvbuf(struct sock *sk, int val)
{
lock_sock(sk);
__sock_set_rcvbuf(sk, val);
release_sock(sk);
}
EXPORT_SYMBOL(sock_set_rcvbuf);
void sock_set_mark(struct sock *sk, u32 val)
{
lock_sock(sk);
sk->sk_mark = val;
release_sock(sk);
}
EXPORT_SYMBOL(sock_set_mark);
/*
* This is meant for all protocols to use and covers goings on
* at the socket level. Everything here is generic.
*/
int sock_setsockopt(struct socket *sock, int level, int optname,
sockptr_t optval, unsigned int optlen)
{
struct sock_txtime sk_txtime;
struct sock *sk = sock->sk;
int val;
int valbool;
struct linger ling;
int ret = 0;
/*
* Options without arguments
*/
if (optname == SO_BINDTODEVICE)
return sock_setbindtodevice(sk, optval, optlen);
if (optlen < sizeof(int))
return -EINVAL;
if (copy_from_sockptr(&val, optval, sizeof(val)))
return -EFAULT;
valbool = val ? 1 : 0;
lock_sock(sk);
switch (optname) {
case SO_DEBUG:
if (val && !capable(CAP_NET_ADMIN))
ret = -EACCES;
else
sock_valbool_flag(sk, SOCK_DBG, valbool);
break;
case SO_REUSEADDR:
sk->sk_reuse = (valbool ? SK_CAN_REUSE : SK_NO_REUSE);
break;
case SO_REUSEPORT:
sk->sk_reuseport = valbool;
break;
case SO_TYPE:
case SO_PROTOCOL:
case SO_DOMAIN:
case SO_ERROR:
ret = -ENOPROTOOPT;
break;
case SO_DONTROUTE:
sock_valbool_flag(sk, SOCK_LOCALROUTE, valbool);
sk_dst_reset(sk);
break;
case SO_BROADCAST:
sock_valbool_flag(sk, SOCK_BROADCAST, valbool);
break;
case SO_SNDBUF:
/* Don't error on this BSD doesn't and if you think
* about it this is right. Otherwise apps have to
* play 'guess the biggest size' games. RCVBUF/SNDBUF
* are treated in BSD as hints
*/
val = min_t(u32, val, sysctl_wmem_max);
set_sndbuf:
sock: consistent handling of extreme SO_SNDBUF/SO_RCVBUF values SO_SNDBUF and SO_RCVBUF (and their *BUFFORCE version) may overflow or underflow their input value. This patch aims at providing explicit handling of these extreme cases, to get a clear behaviour even with values bigger than INT_MAX / 2 or lower than INT_MIN / 2. For simplicity, only SO_SNDBUF and SO_SNDBUFFORCE are described here, but the same explanation and fix apply to SO_RCVBUF and SO_RCVBUFFORCE (with 'SNDBUF' replaced by 'RCVBUF' and 'wmem_max' by 'rmem_max'). Overflow of positive values =========================== When handling SO_SNDBUF or SO_SNDBUFFORCE, if 'val' exceeds INT_MAX / 2, the buffer size is set to its minimum value because 'val * 2' overflows, and max_t() considers that it's smaller than SOCK_MIN_SNDBUF. For SO_SNDBUF, this can only happen with net.core.wmem_max > INT_MAX / 2. SO_SNDBUF and SO_SNDBUFFORCE are actually designed to let users probe for the maximum buffer size by setting an arbitrary large number that gets capped to the maximum allowed/possible size. Having the upper half of the positive integer space to potentially reduce the buffer size to its minimum value defeats this purpose. This patch caps the base value to INT_MAX / 2, so that bigger values don't overflow and keep setting the buffer size to its maximum. Underflow of negative values ============================ For negative numbers, SO_SNDBUF always considers them bigger than net.core.wmem_max, which is bounded by [SOCK_MIN_SNDBUF, INT_MAX]. Therefore such values are set to net.core.wmem_max and we're back to the behaviour of positive integers described above (return maximum buffer size if wmem_max <= INT_MAX / 2, return SOCK_MIN_SNDBUF otherwise). However, SO_SNDBUFFORCE behaves differently. The user value is directly multiplied by two and compared with SOCK_MIN_SNDBUF. If 'val * 2' doesn't underflow or if it underflows to a value smaller than SOCK_MIN_SNDBUF then buffer size is set to its minimum value. Otherwise the buffer size is set to the underflowed value. This patch treats negative values passed to SO_SNDBUFFORCE as null, to prevent underflows. Therefore negative values now always set the buffer size to its minimum value. Even though SO_SNDBUF behaves inconsistently by setting buffer size to the maximum value when passed a negative number, no attempt is made to modify this behaviour. There may exist some programs that rely on using negative numbers to set the maximum buffer size. Avoiding overflows because of extreme net.core.wmem_max values is the most we can do here. Summary of altered behaviours ============================= val : user-space value passed to setsockopt() val_uf : the underflowed value resulting from doubling val when val < INT_MIN / 2 wmem_max : short for net.core.wmem_max val_cap : min(val, wmem_max) min_len : minimal buffer length (that is, SOCK_MIN_SNDBUF) max_len : maximal possible buffer length, regardless of wmem_max (that is, INT_MAX - 1) ^^^^ : altered behaviour SO_SNDBUF: +-------------------------+-------------+------------+----------------+ | CONDITION | OLD RESULT | NEW RESULT | COMMENT | +-------------------------+-------------+------------+----------------+ | val < 0 && | | | No overflow, | | wmem_max <= INT_MAX/2 | wmem_max*2 | wmem_max*2 | keep original | | | | | behaviour | +-------------------------+-------------+------------+----------------+ | val < 0 && | | | Cap wmem_max | | INT_MAX/2 < wmem_max | min_len | max_len | to prevent | | | | ^^^^^^^ | overflow | +-------------------------+-------------+------------+----------------+ | 0 <= val <= min_len/2 | min_len | min_len | Ordinary case | +-------------------------+-------------+------------+----------------+ | min_len/2 < val && | val_cap*2 | val_cap*2 | Ordinary case | | val_cap <= INT_MAX/2 | | | | +-------------------------+-------------+------------+----------------+ | min_len < val && | | | Cap val_cap | | INT_MAX/2 < val_cap | min_len | max_len | again to | | (implies that | | ^^^^^^^ | prevent | | INT_MAX/2 < wmem_max) | | | overflow | +-------------------------+-------------+------------+----------------+ SO_SNDBUFFORCE: +------------------------------+---------+---------+------------------+ | CONDITION | BEFORE | AFTER | COMMENT | | | PATCH | PATCH | | +------------------------------+---------+---------+------------------+ | val < INT_MIN/2 && | min_len | min_len | Underflow with | | val_uf <= min_len | | | no consequence | +------------------------------+---------+---------+------------------+ | val < INT_MIN/2 && | val_uf | min_len | Set val to 0 to | | val_uf > min_len | | ^^^^^^^ | avoid underflow | +------------------------------+---------+---------+------------------+ | INT_MIN/2 <= val < 0 | min_len | min_len | No underflow | +------------------------------+---------+---------+------------------+ | 0 <= val <= min_len/2 | min_len | min_len | Ordinary case | +------------------------------+---------+---------+------------------+ | min_len/2 < val <= INT_MAX/2 | val*2 | val*2 | Ordinary case | +------------------------------+---------+---------+------------------+ | INT_MAX/2 < val | min_len | max_len | Cap val to | | | | ^^^^^^^ | prevent overflow | +------------------------------+---------+---------+------------------+ Signed-off-by: Guillaume Nault <gnault@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-02-13 03:30:34 +00:00
/* Ensure val * 2 fits into an int, to prevent max_t()
* from treating it as a negative value.
*/
val = min_t(int, val, INT_MAX / 2);
sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
WRITE_ONCE(sk->sk_sndbuf,
max_t(int, val * 2, SOCK_MIN_SNDBUF));
/* Wake up sending tasks if we upped the value. */
sk->sk_write_space(sk);
break;
case SO_SNDBUFFORCE:
if (!capable(CAP_NET_ADMIN)) {
ret = -EPERM;
break;
}
sock: consistent handling of extreme SO_SNDBUF/SO_RCVBUF values SO_SNDBUF and SO_RCVBUF (and their *BUFFORCE version) may overflow or underflow their input value. This patch aims at providing explicit handling of these extreme cases, to get a clear behaviour even with values bigger than INT_MAX / 2 or lower than INT_MIN / 2. For simplicity, only SO_SNDBUF and SO_SNDBUFFORCE are described here, but the same explanation and fix apply to SO_RCVBUF and SO_RCVBUFFORCE (with 'SNDBUF' replaced by 'RCVBUF' and 'wmem_max' by 'rmem_max'). Overflow of positive values =========================== When handling SO_SNDBUF or SO_SNDBUFFORCE, if 'val' exceeds INT_MAX / 2, the buffer size is set to its minimum value because 'val * 2' overflows, and max_t() considers that it's smaller than SOCK_MIN_SNDBUF. For SO_SNDBUF, this can only happen with net.core.wmem_max > INT_MAX / 2. SO_SNDBUF and SO_SNDBUFFORCE are actually designed to let users probe for the maximum buffer size by setting an arbitrary large number that gets capped to the maximum allowed/possible size. Having the upper half of the positive integer space to potentially reduce the buffer size to its minimum value defeats this purpose. This patch caps the base value to INT_MAX / 2, so that bigger values don't overflow and keep setting the buffer size to its maximum. Underflow of negative values ============================ For negative numbers, SO_SNDBUF always considers them bigger than net.core.wmem_max, which is bounded by [SOCK_MIN_SNDBUF, INT_MAX]. Therefore such values are set to net.core.wmem_max and we're back to the behaviour of positive integers described above (return maximum buffer size if wmem_max <= INT_MAX / 2, return SOCK_MIN_SNDBUF otherwise). However, SO_SNDBUFFORCE behaves differently. The user value is directly multiplied by two and compared with SOCK_MIN_SNDBUF. If 'val * 2' doesn't underflow or if it underflows to a value smaller than SOCK_MIN_SNDBUF then buffer size is set to its minimum value. Otherwise the buffer size is set to the underflowed value. This patch treats negative values passed to SO_SNDBUFFORCE as null, to prevent underflows. Therefore negative values now always set the buffer size to its minimum value. Even though SO_SNDBUF behaves inconsistently by setting buffer size to the maximum value when passed a negative number, no attempt is made to modify this behaviour. There may exist some programs that rely on using negative numbers to set the maximum buffer size. Avoiding overflows because of extreme net.core.wmem_max values is the most we can do here. Summary of altered behaviours ============================= val : user-space value passed to setsockopt() val_uf : the underflowed value resulting from doubling val when val < INT_MIN / 2 wmem_max : short for net.core.wmem_max val_cap : min(val, wmem_max) min_len : minimal buffer length (that is, SOCK_MIN_SNDBUF) max_len : maximal possible buffer length, regardless of wmem_max (that is, INT_MAX - 1) ^^^^ : altered behaviour SO_SNDBUF: +-------------------------+-------------+------------+----------------+ | CONDITION | OLD RESULT | NEW RESULT | COMMENT | +-------------------------+-------------+------------+----------------+ | val < 0 && | | | No overflow, | | wmem_max <= INT_MAX/2 | wmem_max*2 | wmem_max*2 | keep original | | | | | behaviour | +-------------------------+-------------+------------+----------------+ | val < 0 && | | | Cap wmem_max | | INT_MAX/2 < wmem_max | min_len | max_len | to prevent | | | | ^^^^^^^ | overflow | +-------------------------+-------------+------------+----------------+ | 0 <= val <= min_len/2 | min_len | min_len | Ordinary case | +-------------------------+-------------+------------+----------------+ | min_len/2 < val && | val_cap*2 | val_cap*2 | Ordinary case | | val_cap <= INT_MAX/2 | | | | +-------------------------+-------------+------------+----------------+ | min_len < val && | | | Cap val_cap | | INT_MAX/2 < val_cap | min_len | max_len | again to | | (implies that | | ^^^^^^^ | prevent | | INT_MAX/2 < wmem_max) | | | overflow | +-------------------------+-------------+------------+----------------+ SO_SNDBUFFORCE: +------------------------------+---------+---------+------------------+ | CONDITION | BEFORE | AFTER | COMMENT | | | PATCH | PATCH | | +------------------------------+---------+---------+------------------+ | val < INT_MIN/2 && | min_len | min_len | Underflow with | | val_uf <= min_len | | | no consequence | +------------------------------+---------+---------+------------------+ | val < INT_MIN/2 && | val_uf | min_len | Set val to 0 to | | val_uf > min_len | | ^^^^^^^ | avoid underflow | +------------------------------+---------+---------+------------------+ | INT_MIN/2 <= val < 0 | min_len | min_len | No underflow | +------------------------------+---------+---------+------------------+ | 0 <= val <= min_len/2 | min_len | min_len | Ordinary case | +------------------------------+---------+---------+------------------+ | min_len/2 < val <= INT_MAX/2 | val*2 | val*2 | Ordinary case | +------------------------------+---------+---------+------------------+ | INT_MAX/2 < val | min_len | max_len | Cap val to | | | | ^^^^^^^ | prevent overflow | +------------------------------+---------+---------+------------------+ Signed-off-by: Guillaume Nault <gnault@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-02-13 03:30:34 +00:00
/* No negative values (to prevent underflow, as val will be
* multiplied by 2).
*/
if (val < 0)
val = 0;
goto set_sndbuf;
case SO_RCVBUF:
/* Don't error on this BSD doesn't and if you think
* about it this is right. Otherwise apps have to
* play 'guess the biggest size' games. RCVBUF/SNDBUF
* are treated in BSD as hints
*/
__sock_set_rcvbuf(sk, min_t(u32, val, sysctl_rmem_max));
break;
case SO_RCVBUFFORCE:
if (!capable(CAP_NET_ADMIN)) {
ret = -EPERM;
break;
}
sock: consistent handling of extreme SO_SNDBUF/SO_RCVBUF values SO_SNDBUF and SO_RCVBUF (and their *BUFFORCE version) may overflow or underflow their input value. This patch aims at providing explicit handling of these extreme cases, to get a clear behaviour even with values bigger than INT_MAX / 2 or lower than INT_MIN / 2. For simplicity, only SO_SNDBUF and SO_SNDBUFFORCE are described here, but the same explanation and fix apply to SO_RCVBUF and SO_RCVBUFFORCE (with 'SNDBUF' replaced by 'RCVBUF' and 'wmem_max' by 'rmem_max'). Overflow of positive values =========================== When handling SO_SNDBUF or SO_SNDBUFFORCE, if 'val' exceeds INT_MAX / 2, the buffer size is set to its minimum value because 'val * 2' overflows, and max_t() considers that it's smaller than SOCK_MIN_SNDBUF. For SO_SNDBUF, this can only happen with net.core.wmem_max > INT_MAX / 2. SO_SNDBUF and SO_SNDBUFFORCE are actually designed to let users probe for the maximum buffer size by setting an arbitrary large number that gets capped to the maximum allowed/possible size. Having the upper half of the positive integer space to potentially reduce the buffer size to its minimum value defeats this purpose. This patch caps the base value to INT_MAX / 2, so that bigger values don't overflow and keep setting the buffer size to its maximum. Underflow of negative values ============================ For negative numbers, SO_SNDBUF always considers them bigger than net.core.wmem_max, which is bounded by [SOCK_MIN_SNDBUF, INT_MAX]. Therefore such values are set to net.core.wmem_max and we're back to the behaviour of positive integers described above (return maximum buffer size if wmem_max <= INT_MAX / 2, return SOCK_MIN_SNDBUF otherwise). However, SO_SNDBUFFORCE behaves differently. The user value is directly multiplied by two and compared with SOCK_MIN_SNDBUF. If 'val * 2' doesn't underflow or if it underflows to a value smaller than SOCK_MIN_SNDBUF then buffer size is set to its minimum value. Otherwise the buffer size is set to the underflowed value. This patch treats negative values passed to SO_SNDBUFFORCE as null, to prevent underflows. Therefore negative values now always set the buffer size to its minimum value. Even though SO_SNDBUF behaves inconsistently by setting buffer size to the maximum value when passed a negative number, no attempt is made to modify this behaviour. There may exist some programs that rely on using negative numbers to set the maximum buffer size. Avoiding overflows because of extreme net.core.wmem_max values is the most we can do here. Summary of altered behaviours ============================= val : user-space value passed to setsockopt() val_uf : the underflowed value resulting from doubling val when val < INT_MIN / 2 wmem_max : short for net.core.wmem_max val_cap : min(val, wmem_max) min_len : minimal buffer length (that is, SOCK_MIN_SNDBUF) max_len : maximal possible buffer length, regardless of wmem_max (that is, INT_MAX - 1) ^^^^ : altered behaviour SO_SNDBUF: +-------------------------+-------------+------------+----------------+ | CONDITION | OLD RESULT | NEW RESULT | COMMENT | +-------------------------+-------------+------------+----------------+ | val < 0 && | | | No overflow, | | wmem_max <= INT_MAX/2 | wmem_max*2 | wmem_max*2 | keep original | | | | | behaviour | +-------------------------+-------------+------------+----------------+ | val < 0 && | | | Cap wmem_max | | INT_MAX/2 < wmem_max | min_len | max_len | to prevent | | | | ^^^^^^^ | overflow | +-------------------------+-------------+------------+----------------+ | 0 <= val <= min_len/2 | min_len | min_len | Ordinary case | +-------------------------+-------------+------------+----------------+ | min_len/2 < val && | val_cap*2 | val_cap*2 | Ordinary case | | val_cap <= INT_MAX/2 | | | | +-------------------------+-------------+------------+----------------+ | min_len < val && | | | Cap val_cap | | INT_MAX/2 < val_cap | min_len | max_len | again to | | (implies that | | ^^^^^^^ | prevent | | INT_MAX/2 < wmem_max) | | | overflow | +-------------------------+-------------+------------+----------------+ SO_SNDBUFFORCE: +------------------------------+---------+---------+------------------+ | CONDITION | BEFORE | AFTER | COMMENT | | | PATCH | PATCH | | +------------------------------+---------+---------+------------------+ | val < INT_MIN/2 && | min_len | min_len | Underflow with | | val_uf <= min_len | | | no consequence | +------------------------------+---------+---------+------------------+ | val < INT_MIN/2 && | val_uf | min_len | Set val to 0 to | | val_uf > min_len | | ^^^^^^^ | avoid underflow | +------------------------------+---------+---------+------------------+ | INT_MIN/2 <= val < 0 | min_len | min_len | No underflow | +------------------------------+---------+---------+------------------+ | 0 <= val <= min_len/2 | min_len | min_len | Ordinary case | +------------------------------+---------+---------+------------------+ | min_len/2 < val <= INT_MAX/2 | val*2 | val*2 | Ordinary case | +------------------------------+---------+---------+------------------+ | INT_MAX/2 < val | min_len | max_len | Cap val to | | | | ^^^^^^^ | prevent overflow | +------------------------------+---------+---------+------------------+ Signed-off-by: Guillaume Nault <gnault@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-02-13 03:30:34 +00:00
/* No negative values (to prevent underflow, as val will be
* multiplied by 2).
*/
__sock_set_rcvbuf(sk, max(val, 0));
break;
case SO_KEEPALIVE:
if (sk->sk_prot->keepalive)
sk->sk_prot->keepalive(sk, valbool);
sock_valbool_flag(sk, SOCK_KEEPOPEN, valbool);
break;
case SO_OOBINLINE:
sock_valbool_flag(sk, SOCK_URGINLINE, valbool);
break;
case SO_NO_CHECK:
sk->sk_no_check_tx = valbool;
break;
case SO_PRIORITY:
if ((val >= 0 && val <= 6) ||
ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
sk->sk_priority = val;
else
ret = -EPERM;
break;
case SO_LINGER:
if (optlen < sizeof(ling)) {
ret = -EINVAL; /* 1003.1g */
break;
}
if (copy_from_sockptr(&ling, optval, sizeof(ling))) {
ret = -EFAULT;
break;
}
if (!ling.l_onoff)
sock_reset_flag(sk, SOCK_LINGER);
else {
#if (BITS_PER_LONG == 32)
if ((unsigned int)ling.l_linger >= MAX_SCHEDULE_TIMEOUT/HZ)
sk->sk_lingertime = MAX_SCHEDULE_TIMEOUT;
else
#endif
sk->sk_lingertime = (unsigned int)ling.l_linger * HZ;
sock_set_flag(sk, SOCK_LINGER);
}
break;
case SO_BSDCOMPAT:
break;
case SO_PASSCRED:
if (valbool)
set_bit(SOCK_PASSCRED, &sock->flags);
else
clear_bit(SOCK_PASSCRED, &sock->flags);
break;
case SO_TIMESTAMP_OLD:
__sock_set_timestamps(sk, valbool, false, false);
break;
case SO_TIMESTAMP_NEW:
__sock_set_timestamps(sk, valbool, true, false);
break;
case SO_TIMESTAMPNS_OLD:
__sock_set_timestamps(sk, valbool, false, true);
break;
case SO_TIMESTAMPNS_NEW:
__sock_set_timestamps(sk, valbool, true, true);
break;
case SO_TIMESTAMPING_NEW:
case SO_TIMESTAMPING_OLD:
if (val & ~SOF_TIMESTAMPING_MASK) {
ret = -EINVAL;
break;
}
if (val & SOF_TIMESTAMPING_OPT_ID &&
net-timestamp: TCP timestamping TCP timestamping extends SO_TIMESTAMPING to bytestreams. Bytestreams do not have a 1:1 relationship between send() buffers and network packets. The feature interprets a send call on a bytestream as a request for a timestamp for the last byte in that send() buffer. The choice corresponds to a request for a timestamp when all bytes in the buffer have been sent. That assumption depends on in-order kernel transmission. This is the common case. That said, it is possible to construct a traffic shaping tree that would result in reordering. The guarantee is strong, then, but not ironclad. This implementation supports send and sendpages (splice). GSO replaces one large packet with multiple smaller packets. This patch also copies the option into the correct smaller packet. This patch does not yet support timestamping on data in an initial TCP Fast Open SYN, because that takes a very different data path. If ID generation in ee_data is enabled, bytestream timestamps return a byte offset, instead of the packet counter for datagrams. The implementation supports a single timestamp per packet. It silenty replaces requests for previous timestamps. To avoid missing tstamps, flush the tcp queue by disabling Nagle, cork and autocork. Missing tstamps can be detected by offset when the ee_data ID is enabled. Implementation details: - On GSO, the timestamping code can be included in the main loop. I moved it into its own loop to reduce the impact on the common case to a single branch. - To avoid leaking the absolute seqno to userspace, the offset returned in ee_data must always be relative. It is an offset between an skb and sk field. The first is always set (also for GSO & ACK). The second must also never be uninitialized. Only allow the ID option on sockets in the ESTABLISHED state, for which the seqno is available. Never reset it to zero (instead, move it to the current seqno when reenabling the option). Signed-off-by: Willem de Bruijn <willemb@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-08-05 02:11:49 +00:00
!(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)) {
if (sk->sk_protocol == IPPROTO_TCP &&
sk->sk_type == SOCK_STREAM) {
if ((1 << sk->sk_state) &
(TCPF_CLOSE | TCPF_LISTEN)) {
net-timestamp: TCP timestamping TCP timestamping extends SO_TIMESTAMPING to bytestreams. Bytestreams do not have a 1:1 relationship between send() buffers and network packets. The feature interprets a send call on a bytestream as a request for a timestamp for the last byte in that send() buffer. The choice corresponds to a request for a timestamp when all bytes in the buffer have been sent. That assumption depends on in-order kernel transmission. This is the common case. That said, it is possible to construct a traffic shaping tree that would result in reordering. The guarantee is strong, then, but not ironclad. This implementation supports send and sendpages (splice). GSO replaces one large packet with multiple smaller packets. This patch also copies the option into the correct smaller packet. This patch does not yet support timestamping on data in an initial TCP Fast Open SYN, because that takes a very different data path. If ID generation in ee_data is enabled, bytestream timestamps return a byte offset, instead of the packet counter for datagrams. The implementation supports a single timestamp per packet. It silenty replaces requests for previous timestamps. To avoid missing tstamps, flush the tcp queue by disabling Nagle, cork and autocork. Missing tstamps can be detected by offset when the ee_data ID is enabled. Implementation details: - On GSO, the timestamping code can be included in the main loop. I moved it into its own loop to reduce the impact on the common case to a single branch. - To avoid leaking the absolute seqno to userspace, the offset returned in ee_data must always be relative. It is an offset between an skb and sk field. The first is always set (also for GSO & ACK). The second must also never be uninitialized. Only allow the ID option on sockets in the ESTABLISHED state, for which the seqno is available. Never reset it to zero (instead, move it to the current seqno when reenabling the option). Signed-off-by: Willem de Bruijn <willemb@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-08-05 02:11:49 +00:00
ret = -EINVAL;
break;
}
sk->sk_tskey = tcp_sk(sk)->snd_una;
} else {
sk->sk_tskey = 0;
}
}
if (val & SOF_TIMESTAMPING_OPT_STATS &&
!(val & SOF_TIMESTAMPING_OPT_TSONLY)) {
ret = -EINVAL;
break;
}
sk->sk_tsflags = val;
sock_valbool_flag(sk, SOCK_TSTAMP_NEW, optname == SO_TIMESTAMPING_NEW);
if (val & SOF_TIMESTAMPING_RX_SOFTWARE)
sock_enable_timestamp(sk,
SOCK_TIMESTAMPING_RX_SOFTWARE);
else
sock_disable_timestamp(sk,
(1UL << SOCK_TIMESTAMPING_RX_SOFTWARE));
break;
case SO_RCVLOWAT:
if (val < 0)
val = INT_MAX;
if (sock->ops->set_rcvlowat)
ret = sock->ops->set_rcvlowat(sk, val);
else
WRITE_ONCE(sk->sk_rcvlowat, val ? : 1);
break;
case SO_RCVTIMEO_OLD:
case SO_RCVTIMEO_NEW:
ret = sock_set_timeout(&sk->sk_rcvtimeo, optval,
optlen, optname == SO_RCVTIMEO_OLD);
break;
case SO_SNDTIMEO_OLD:
case SO_SNDTIMEO_NEW:
ret = sock_set_timeout(&sk->sk_sndtimeo, optval,
optlen, optname == SO_SNDTIMEO_OLD);
break;
case SO_ATTACH_FILTER: {
struct sock_fprog fprog;
ret = copy_bpf_fprog_from_user(&fprog, optval, optlen);
if (!ret)
ret = sk_attach_filter(&fprog, sk);
break;
}
case SO_ATTACH_BPF:
ret = -EINVAL;
if (optlen == sizeof(u32)) {
u32 ufd;
ret = -EFAULT;
if (copy_from_sockptr(&ufd, optval, sizeof(ufd)))
break;
ret = sk_attach_bpf(ufd, sk);
}
break;
case SO_ATTACH_REUSEPORT_CBPF: {
struct sock_fprog fprog;
ret = copy_bpf_fprog_from_user(&fprog, optval, optlen);
if (!ret)
ret = sk_reuseport_attach_filter(&fprog, sk);
break;
}
case SO_ATTACH_REUSEPORT_EBPF:
ret = -EINVAL;
if (optlen == sizeof(u32)) {
u32 ufd;
ret = -EFAULT;
if (copy_from_sockptr(&ufd, optval, sizeof(ufd)))
break;
ret = sk_reuseport_attach_bpf(ufd, sk);
}
break;
case SO_DETACH_REUSEPORT_BPF:
ret = reuseport_detach_prog(sk);
break;
case SO_DETACH_FILTER:
ret = sk_detach_filter(sk);
break;
case SO_LOCK_FILTER:
if (sock_flag(sk, SOCK_FILTER_LOCKED) && !valbool)
ret = -EPERM;
else
sock_valbool_flag(sk, SOCK_FILTER_LOCKED, valbool);
break;
case SO_PASSSEC:
if (valbool)
set_bit(SOCK_PASSSEC, &sock->flags);
else
clear_bit(SOCK_PASSSEC, &sock->flags);
break;
case SO_MARK:
if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
ret = -EPERM;
} else if (val != sk->sk_mark) {
sk->sk_mark = val;
sk_dst_reset(sk);
}
break;
[AF_UNIX]: Datagram getpeersec This patch implements an API whereby an application can determine the label of its peer's Unix datagram sockets via the auxiliary data mechanism of recvmsg. Patch purpose: This patch enables a security-aware application to retrieve the security context of the peer of a Unix datagram socket. The application can then use this security context to determine the security context for processing on behalf of the peer who sent the packet. Patch design and implementation: The design and implementation is very similar to the UDP case for INET sockets. Basically we build upon the existing Unix domain socket API for retrieving user credentials. Linux offers the API for obtaining user credentials via ancillary messages (i.e., out of band/control messages that are bundled together with a normal message). To retrieve the security context, the application first indicates to the kernel such desire by setting the SO_PASSSEC option via getsockopt. Then the application retrieves the security context using the auxiliary data mechanism. An example server application for Unix datagram socket should look like this: toggle = 1; toggle_len = sizeof(toggle); setsockopt(sockfd, SOL_SOCKET, SO_PASSSEC, &toggle, &toggle_len); recvmsg(sockfd, &msg_hdr, 0); if (msg_hdr.msg_controllen > sizeof(struct cmsghdr)) { cmsg_hdr = CMSG_FIRSTHDR(&msg_hdr); if (cmsg_hdr->cmsg_len <= CMSG_LEN(sizeof(scontext)) && cmsg_hdr->cmsg_level == SOL_SOCKET && cmsg_hdr->cmsg_type == SCM_SECURITY) { memcpy(&scontext, CMSG_DATA(cmsg_hdr), sizeof(scontext)); } } sock_setsockopt is enhanced with a new socket option SOCK_PASSSEC to allow a server socket to receive security context of the peer. Testing: We have tested the patch by setting up Unix datagram client and server applications. We verified that the server can retrieve the security context using the auxiliary data mechanism of recvmsg. Signed-off-by: Catherine Zhang <cxzhang@watson.ibm.com> Acked-by: Acked-by: James Morris <jmorris@namei.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-29 19:27:47 +00:00
net: Generalize socket rx gap / receive queue overflow cmsg Create a new socket level option to report number of queue overflows Recently I augmented the AF_PACKET protocol to report the number of frames lost on the socket receive queue between any two enqueued frames. This value was exported via a SOL_PACKET level cmsg. AFter I completed that work it was requested that this feature be generalized so that any datagram oriented socket could make use of this option. As such I've created this patch, It creates a new SOL_SOCKET level option called SO_RXQ_OVFL, which when enabled exports a SOL_SOCKET level cmsg that reports the nubmer of times the sk_receive_queue overflowed between any two given frames. It also augments the AF_PACKET protocol to take advantage of this new feature (as it previously did not touch sk->sk_drops, which this patch uses to record the overflow count). Tested successfully by me. Notes: 1) Unlike my previous patch, this patch simply records the sk_drops value, which is not a number of drops between packets, but rather a total number of drops. Deltas must be computed in user space. 2) While this patch currently works with datagram oriented protocols, it will also be accepted by non-datagram oriented protocols. I'm not sure if thats agreeable to everyone, but my argument in favor of doing so is that, for those protocols which aren't applicable to this option, sk_drops will always be zero, and reporting no drops on a receive queue that isn't used for those non-participating protocols seems reasonable to me. This also saves us having to code in a per-protocol opt in mechanism. 3) This applies cleanly to net-next assuming that commit 977750076d98c7ff6cbda51858bb5a5894a9d9ab (my af packet cmsg patch) is reverted Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-10-12 20:26:31 +00:00
case SO_RXQ_OVFL:
sock_valbool_flag(sk, SOCK_RXQ_OVFL, valbool);
net: Generalize socket rx gap / receive queue overflow cmsg Create a new socket level option to report number of queue overflows Recently I augmented the AF_PACKET protocol to report the number of frames lost on the socket receive queue between any two enqueued frames. This value was exported via a SOL_PACKET level cmsg. AFter I completed that work it was requested that this feature be generalized so that any datagram oriented socket could make use of this option. As such I've created this patch, It creates a new SOL_SOCKET level option called SO_RXQ_OVFL, which when enabled exports a SOL_SOCKET level cmsg that reports the nubmer of times the sk_receive_queue overflowed between any two given frames. It also augments the AF_PACKET protocol to take advantage of this new feature (as it previously did not touch sk->sk_drops, which this patch uses to record the overflow count). Tested successfully by me. Notes: 1) Unlike my previous patch, this patch simply records the sk_drops value, which is not a number of drops between packets, but rather a total number of drops. Deltas must be computed in user space. 2) While this patch currently works with datagram oriented protocols, it will also be accepted by non-datagram oriented protocols. I'm not sure if thats agreeable to everyone, but my argument in favor of doing so is that, for those protocols which aren't applicable to this option, sk_drops will always be zero, and reporting no drops on a receive queue that isn't used for those non-participating protocols seems reasonable to me. This also saves us having to code in a per-protocol opt in mechanism. 3) This applies cleanly to net-next assuming that commit 977750076d98c7ff6cbda51858bb5a5894a9d9ab (my af packet cmsg patch) is reverted Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-10-12 20:26:31 +00:00
break;
case SO_WIFI_STATUS:
sock_valbool_flag(sk, SOCK_WIFI_STATUS, valbool);
break;
case SO_PEEK_OFF:
if (sock->ops->set_peek_off)
ret = sock->ops->set_peek_off(sk, val);
else
ret = -EOPNOTSUPP;
break;
case SO_NOFCS:
sock_valbool_flag(sk, SOCK_NOFCS, valbool);
break;
case SO_SELECT_ERR_QUEUE:
sock_valbool_flag(sk, SOCK_SELECT_ERR_QUEUE, valbool);
break;
#ifdef CONFIG_NET_RX_BUSY_POLL
case SO_BUSY_POLL:
/* allow unprivileged users to decrease the value */
if ((val > sk->sk_ll_usec) && !capable(CAP_NET_ADMIN))
ret = -EPERM;
else {
if (val < 0)
ret = -EINVAL;
else
sk->sk_ll_usec = val;
}
break;
net: Introduce preferred busy-polling The existing busy-polling mode, enabled by the SO_BUSY_POLL socket option or system-wide using the /proc/sys/net/core/busy_read knob, is an opportunistic. That means that if the NAPI context is not scheduled, it will poll it. If, after busy-polling, the budget is exceeded the busy-polling logic will schedule the NAPI onto the regular softirq handling. One implication of the behavior above is that a busy/heavy loaded NAPI context will never enter/allow for busy-polling. Some applications prefer that most NAPI processing would be done by busy-polling. This series adds a new socket option, SO_PREFER_BUSY_POLL, that works in concert with the napi_defer_hard_irqs and gro_flush_timeout knobs. The napi_defer_hard_irqs and gro_flush_timeout knobs were introduced in commit 6f8b12d661d0 ("net: napi: add hard irqs deferral feature"), and allows for a user to defer interrupts to be enabled and instead schedule the NAPI context from a watchdog timer. When a user enables the SO_PREFER_BUSY_POLL, again with the other knobs enabled, and the NAPI context is being processed by a softirq, the softirq NAPI processing will exit early to allow the busy-polling to be performed. If the application stops performing busy-polling via a system call, the watchdog timer defined by gro_flush_timeout will timeout, and regular softirq handling will resume. In summary; Heavy traffic applications that prefer busy-polling over softirq processing should use this option. Example usage: $ echo 2 | sudo tee /sys/class/net/ens785f1/napi_defer_hard_irqs $ echo 200000 | sudo tee /sys/class/net/ens785f1/gro_flush_timeout Note that the timeout should be larger than the userspace processing window, otherwise the watchdog will timeout and fall back to regular softirq processing. Enable the SO_BUSY_POLL/SO_PREFER_BUSY_POLL options on your socket. Signed-off-by: Björn Töpel <bjorn.topel@intel.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Jakub Kicinski <kuba@kernel.org> Link: https://lore.kernel.org/bpf/20201130185205.196029-2-bjorn.topel@gmail.com
2020-11-30 18:51:56 +00:00
case SO_PREFER_BUSY_POLL:
if (valbool && !capable(CAP_NET_ADMIN))
ret = -EPERM;
else
WRITE_ONCE(sk->sk_prefer_busy_poll, valbool);
break;
case SO_BUSY_POLL_BUDGET:
if (val > READ_ONCE(sk->sk_busy_poll_budget) && !capable(CAP_NET_ADMIN)) {
ret = -EPERM;
} else {
if (val < 0 || val > U16_MAX)
ret = -EINVAL;
else
WRITE_ONCE(sk->sk_busy_poll_budget, val);
}
break;
#endif
case SO_MAX_PACING_RATE:
{
unsigned long ulval = (val == ~0U) ? ~0UL : (unsigned int)val;
if (sizeof(ulval) != sizeof(val) &&
optlen >= sizeof(ulval) &&
copy_from_sockptr(&ulval, optval, sizeof(ulval))) {
ret = -EFAULT;
break;
}
if (ulval != ~0UL)
tcp: internal implementation for pacing BBR congestion control depends on pacing, and pacing is currently handled by sch_fq packet scheduler for performance reasons, and also because implemening pacing with FQ was convenient to truly avoid bursts. However there are many cases where this packet scheduler constraint is not practical. - Many linux hosts are not focusing on handling thousands of TCP flows in the most efficient way. - Some routers use fq_codel or other AQM, but still would like to use BBR for the few TCP flows they initiate/terminate. This patch implements an automatic fallback to internal pacing. Pacing is requested either by BBR or use of SO_MAX_PACING_RATE option. If sch_fq happens to be in the egress path, pacing is delegated to the qdisc, otherwise pacing is done by TCP itself. One advantage of pacing from TCP stack is to get more precise rtt estimations, and less work done from TX completion, since TCP Small queue limits are not generally hit. Setups with single TX queue but many cpus might even benefit from this. Note that unlike sch_fq, we do not take into account header sizes. Taking care of these headers would add additional complexity for no practical differences in behavior. Some performance numbers using 800 TCP_STREAM flows rate limited to ~48 Mbit per second on 40Gbit NIC. If MQ+pfifo_fast is used on the NIC : $ sar -n DEV 1 5 | grep eth 14:48:44 eth0 725743.00 2932134.00 46776.76 4335184.68 0.00 0.00 1.00 14:48:45 eth0 725349.00 2932112.00 46751.86 4335158.90 0.00 0.00 0.00 14:48:46 eth0 725101.00 2931153.00 46735.07 4333748.63 0.00 0.00 0.00 14:48:47 eth0 725099.00 2931161.00 46735.11 4333760.44 0.00 0.00 1.00 14:48:48 eth0 725160.00 2931731.00 46738.88 4334606.07 0.00 0.00 0.00 Average: eth0 725290.40 2931658.20 46747.54 4334491.74 0.00 0.00 0.40 $ vmstat 1 5 procs -----------memory---------- ---swap-- -----io---- -system-- ------cpu----- r b swpd free buff cache si so bi bo in cs us sy id wa st 4 0 0 259825920 45644 2708324 0 0 21 2 247 98 0 0 100 0 0 4 0 0 259823744 45644 2708356 0 0 0 0 2400825 159843 0 19 81 0 0 0 0 0 259824208 45644 2708072 0 0 0 0 2407351 159929 0 19 81 0 0 1 0 0 259824592 45644 2708128 0 0 0 0 2405183 160386 0 19 80 0 0 1 0 0 259824272 45644 2707868 0 0 0 32 2396361 158037 0 19 81 0 0 Now use MQ+FQ : lpaa23:~# echo fq >/proc/sys/net/core/default_qdisc lpaa23:~# tc qdisc replace dev eth0 root mq $ sar -n DEV 1 5 | grep eth 14:49:57 eth0 678614.00 2727930.00 43739.13 4033279.14 0.00 0.00 0.00 14:49:58 eth0 677620.00 2723971.00 43674.69 4027429.62 0.00 0.00 1.00 14:49:59 eth0 676396.00 2719050.00 43596.83 4020125.02 0.00 0.00 0.00 14:50:00 eth0 675197.00 2714173.00 43518.62 4012938.90 0.00 0.00 1.00 14:50:01 eth0 676388.00 2719063.00 43595.47 4020171.64 0.00 0.00 0.00 Average: eth0 676843.00 2720837.40 43624.95 4022788.86 0.00 0.00 0.40 $ vmstat 1 5 procs -----------memory---------- ---swap-- -----io---- -system-- ------cpu----- r b swpd free buff cache si so bi bo in cs us sy id wa st 2 0 0 259832240 46008 2710912 0 0 21 2 223 192 0 1 99 0 0 1 0 0 259832896 46008 2710744 0 0 0 0 1702206 198078 0 17 82 0 0 0 0 0 259830272 46008 2710596 0 0 0 0 1696340 197756 1 17 83 0 0 4 0 0 259829168 46024 2710584 0 0 16 0 1688472 197158 1 17 82 0 0 3 0 0 259830224 46024 2710408 0 0 0 0 1692450 197212 0 18 82 0 0 As expected, number of interrupts per second is very different. Signed-off-by: Eric Dumazet <edumazet@google.com> Acked-by: Soheil Hassas Yeganeh <soheil@google.com> Cc: Neal Cardwell <ncardwell@google.com> Cc: Yuchung Cheng <ycheng@google.com> Cc: Van Jacobson <vanj@google.com> Cc: Jerry Chu <hkchu@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-05-16 11:24:36 +00:00
cmpxchg(&sk->sk_pacing_status,
SK_PACING_NONE,
SK_PACING_NEEDED);
sk->sk_max_pacing_rate = ulval;
sk->sk_pacing_rate = min(sk->sk_pacing_rate, ulval);
break;
}
case SO_INCOMING_CPU:
net: annotate accesses to sk->sk_incoming_cpu This socket field can be read and written by concurrent cpus. Use READ_ONCE() and WRITE_ONCE() annotations to document this, and avoid some compiler 'optimizations'. KCSAN reported : BUG: KCSAN: data-race in tcp_v4_rcv / tcp_v4_rcv write to 0xffff88812220763c of 4 bytes by interrupt on cpu 0: sk_incoming_cpu_update include/net/sock.h:953 [inline] tcp_v4_rcv+0x1b3c/0x1bb0 net/ipv4/tcp_ipv4.c:1934 ip_protocol_deliver_rcu+0x4d/0x420 net/ipv4/ip_input.c:204 ip_local_deliver_finish+0x110/0x140 net/ipv4/ip_input.c:231 NF_HOOK include/linux/netfilter.h:305 [inline] NF_HOOK include/linux/netfilter.h:299 [inline] ip_local_deliver+0x133/0x210 net/ipv4/ip_input.c:252 dst_input include/net/dst.h:442 [inline] ip_rcv_finish+0x121/0x160 net/ipv4/ip_input.c:413 NF_HOOK include/linux/netfilter.h:305 [inline] NF_HOOK include/linux/netfilter.h:299 [inline] ip_rcv+0x18f/0x1a0 net/ipv4/ip_input.c:523 __netif_receive_skb_one_core+0xa7/0xe0 net/core/dev.c:5010 __netif_receive_skb+0x37/0xf0 net/core/dev.c:5124 process_backlog+0x1d3/0x420 net/core/dev.c:5955 napi_poll net/core/dev.c:6392 [inline] net_rx_action+0x3ae/0xa90 net/core/dev.c:6460 __do_softirq+0x115/0x33f kernel/softirq.c:292 do_softirq_own_stack+0x2a/0x40 arch/x86/entry/entry_64.S:1082 do_softirq.part.0+0x6b/0x80 kernel/softirq.c:337 do_softirq kernel/softirq.c:329 [inline] __local_bh_enable_ip+0x76/0x80 kernel/softirq.c:189 read to 0xffff88812220763c of 4 bytes by interrupt on cpu 1: sk_incoming_cpu_update include/net/sock.h:952 [inline] tcp_v4_rcv+0x181a/0x1bb0 net/ipv4/tcp_ipv4.c:1934 ip_protocol_deliver_rcu+0x4d/0x420 net/ipv4/ip_input.c:204 ip_local_deliver_finish+0x110/0x140 net/ipv4/ip_input.c:231 NF_HOOK include/linux/netfilter.h:305 [inline] NF_HOOK include/linux/netfilter.h:299 [inline] ip_local_deliver+0x133/0x210 net/ipv4/ip_input.c:252 dst_input include/net/dst.h:442 [inline] ip_rcv_finish+0x121/0x160 net/ipv4/ip_input.c:413 NF_HOOK include/linux/netfilter.h:305 [inline] NF_HOOK include/linux/netfilter.h:299 [inline] ip_rcv+0x18f/0x1a0 net/ipv4/ip_input.c:523 __netif_receive_skb_one_core+0xa7/0xe0 net/core/dev.c:5010 __netif_receive_skb+0x37/0xf0 net/core/dev.c:5124 process_backlog+0x1d3/0x420 net/core/dev.c:5955 napi_poll net/core/dev.c:6392 [inline] net_rx_action+0x3ae/0xa90 net/core/dev.c:6460 __do_softirq+0x115/0x33f kernel/softirq.c:292 run_ksoftirqd+0x46/0x60 kernel/softirq.c:603 smpboot_thread_fn+0x37d/0x4a0 kernel/smpboot.c:165 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 16 Comm: ksoftirqd/1 Not tainted 5.4.0-rc3+ #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-10-30 20:00:04 +00:00
WRITE_ONCE(sk->sk_incoming_cpu, val);
break;
case SO_CNX_ADVICE:
if (val == 1)
dst_negative_advice(sk);
break;
case SO_ZEROCOPY:
if (sk->sk_family == PF_INET || sk->sk_family == PF_INET6) {
if (!((sk->sk_type == SOCK_STREAM &&
sk->sk_protocol == IPPROTO_TCP) ||
(sk->sk_type == SOCK_DGRAM &&
sk->sk_protocol == IPPROTO_UDP)))
ret = -ENOTSUPP;
} else if (sk->sk_family != PF_RDS) {
ret = -ENOTSUPP;
}
if (!ret) {
if (val < 0 || val > 1)
ret = -EINVAL;
else
sock_valbool_flag(sk, SOCK_ZEROCOPY, valbool);
}
break;
case SO_TXTIME:
if (optlen != sizeof(struct sock_txtime)) {
ret = -EINVAL;
break;
} else if (copy_from_sockptr(&sk_txtime, optval,
sizeof(struct sock_txtime))) {
ret = -EFAULT;
break;
} else if (sk_txtime.flags & ~SOF_TXTIME_FLAGS_MASK) {
ret = -EINVAL;
break;
}
/* CLOCK_MONOTONIC is only used by sch_fq, and this packet
* scheduler has enough safe guards.
*/
if (sk_txtime.clockid != CLOCK_MONOTONIC &&
!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
ret = -EPERM;
break;
}
sock_valbool_flag(sk, SOCK_TXTIME, true);
sk->sk_clockid = sk_txtime.clockid;
sk->sk_txtime_deadline_mode =
!!(sk_txtime.flags & SOF_TXTIME_DEADLINE_MODE);
sk->sk_txtime_report_errors =
!!(sk_txtime.flags & SOF_TXTIME_REPORT_ERRORS);
break;
net: introduce SO_BINDTOIFINDEX sockopt This introduces a new generic SOL_SOCKET-level socket option called SO_BINDTOIFINDEX. It behaves similar to SO_BINDTODEVICE, but takes a network interface index as argument, rather than the network interface name. User-space often refers to network-interfaces via their index, but has to temporarily resolve it to a name for a call into SO_BINDTODEVICE. This might pose problems when the network-device is renamed asynchronously by other parts of the system. When this happens, the SO_BINDTODEVICE might either fail, or worse, it might bind to the wrong device. In most cases user-space only ever operates on devices which they either manage themselves, or otherwise have a guarantee that the device name will not change (e.g., devices that are UP cannot be renamed). However, particularly in libraries this guarantee is non-obvious and it would be nice if that race-condition would simply not exist. It would make it easier for those libraries to operate even in situations where the device-name might change under the hood. A real use-case that we recently hit is trying to start the network stack early in the initrd but make it survive into the real system. Existing distributions rename network-interfaces during the transition from initrd into the real system. This, obviously, cannot affect devices that are up and running (unless you also consider moving them between network-namespaces). However, the network manager now has to make sure its management engine for dormant devices will not run in parallel to these renames. Particularly, when you offload operations like DHCP into separate processes, these might setup their sockets early, and thus have to resolve the device-name possibly running into this race-condition. By avoiding a call to resolve the device-name, we no longer depend on the name and can run network setup of dormant devices in parallel to the transition off the initrd. The SO_BINDTOIFINDEX ioctl plugs this race. Reviewed-by: Tom Gundersen <teg@jklm.no> Signed-off-by: David Herrmann <dh.herrmann@gmail.com> Acked-by: Willem de Bruijn <willemb@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-01-15 13:42:14 +00:00
case SO_BINDTOIFINDEX:
ret = sock_bindtoindex_locked(sk, val);
net: introduce SO_BINDTOIFINDEX sockopt This introduces a new generic SOL_SOCKET-level socket option called SO_BINDTOIFINDEX. It behaves similar to SO_BINDTODEVICE, but takes a network interface index as argument, rather than the network interface name. User-space often refers to network-interfaces via their index, but has to temporarily resolve it to a name for a call into SO_BINDTODEVICE. This might pose problems when the network-device is renamed asynchronously by other parts of the system. When this happens, the SO_BINDTODEVICE might either fail, or worse, it might bind to the wrong device. In most cases user-space only ever operates on devices which they either manage themselves, or otherwise have a guarantee that the device name will not change (e.g., devices that are UP cannot be renamed). However, particularly in libraries this guarantee is non-obvious and it would be nice if that race-condition would simply not exist. It would make it easier for those libraries to operate even in situations where the device-name might change under the hood. A real use-case that we recently hit is trying to start the network stack early in the initrd but make it survive into the real system. Existing distributions rename network-interfaces during the transition from initrd into the real system. This, obviously, cannot affect devices that are up and running (unless you also consider moving them between network-namespaces). However, the network manager now has to make sure its management engine for dormant devices will not run in parallel to these renames. Particularly, when you offload operations like DHCP into separate processes, these might setup their sockets early, and thus have to resolve the device-name possibly running into this race-condition. By avoiding a call to resolve the device-name, we no longer depend on the name and can run network setup of dormant devices in parallel to the transition off the initrd. The SO_BINDTOIFINDEX ioctl plugs this race. Reviewed-by: Tom Gundersen <teg@jklm.no> Signed-off-by: David Herrmann <dh.herrmann@gmail.com> Acked-by: Willem de Bruijn <willemb@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-01-15 13:42:14 +00:00
break;
default:
ret = -ENOPROTOOPT;
break;
}
release_sock(sk);
return ret;
}
EXPORT_SYMBOL(sock_setsockopt);
static void cred_to_ucred(struct pid *pid, const struct cred *cred,
struct ucred *ucred)
{
ucred->pid = pid_vnr(pid);
ucred->uid = ucred->gid = -1;
if (cred) {
struct user_namespace *current_ns = current_user_ns();
ucred->uid = from_kuid_munged(current_ns, cred->euid);
ucred->gid = from_kgid_munged(current_ns, cred->egid);
}
}
net: introduce SO_PEERGROUPS getsockopt This adds the new getsockopt(2) option SO_PEERGROUPS on SOL_SOCKET to retrieve the auxiliary groups of the remote peer. It is designed to naturally extend SO_PEERCRED. That is, the underlying data is from the same credentials. Regarding its syntax, it is based on SO_PEERSEC. That is, if the provided buffer is too small, ERANGE is returned and @optlen is updated. Otherwise, the information is copied, @optlen is set to the actual size, and 0 is returned. While SO_PEERCRED (and thus `struct ucred') already returns the primary group, it lacks the auxiliary group vector. However, nearly all access controls (including kernel side VFS and SYSVIPC, but also user-space polkit, DBus, ...) consider the entire set of groups, rather than just the primary group. But this is currently not possible with pure SO_PEERCRED. Instead, user-space has to work around this and query the system database for the auxiliary groups of a UID retrieved via SO_PEERCRED. Unfortunately, there is no race-free way to query the auxiliary groups of the PID/UID retrieved via SO_PEERCRED. Hence, the current user-space solution is to use getgrouplist(3p), which itself falls back to NSS and whatever is configured in nsswitch.conf(3). This effectively checks which groups we *would* assign to the user if it logged in *now*. On normal systems it is as easy as reading /etc/group, but with NSS it can resort to quering network databases (eg., LDAP), using IPC or network communication. Long story short: Whenever we want to use auxiliary groups for access checks on IPC, we need further IPC to talk to the user/group databases, rather than just relying on SO_PEERCRED and the incoming socket. This is unfortunate, and might even result in dead-locks if the database query uses the same IPC as the original request. So far, those recursions / dead-locks have been avoided by using primitive IPC for all crucial NSS modules. However, we want to avoid re-inventing the wheel for each NSS module that might be involved in user/group queries. Hence, we would preferably make DBus (and other IPC that supports access-management based on groups) work without resorting to the user/group database. This new SO_PEERGROUPS ioctl would allow us to make dbus-daemon work without ever calling into NSS. Cc: Michal Sekletar <msekleta@redhat.com> Cc: Simon McVittie <simon.mcvittie@collabora.co.uk> Reviewed-by: Tom Gundersen <teg@jklm.no> Signed-off-by: David Herrmann <dh.herrmann@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-06-21 08:47:15 +00:00
static int groups_to_user(gid_t __user *dst, const struct group_info *src)
{
struct user_namespace *user_ns = current_user_ns();
int i;
for (i = 0; i < src->ngroups; i++)
if (put_user(from_kgid_munged(user_ns, src->gid[i]), dst + i))
return -EFAULT;
return 0;
}
int sock_getsockopt(struct socket *sock, int level, int optname,
char __user *optval, int __user *optlen)
{
struct sock *sk = sock->sk;
union {
int val;
u64 val64;
unsigned long ulval;
struct linger ling;
struct old_timeval32 tm32;
struct __kernel_old_timeval tm;
struct __kernel_sock_timeval stm;
struct sock_txtime txtime;
} v;
int lv = sizeof(int);
int len;
if (get_user(len, optlen))
return -EFAULT;
if (len < 0)
return -EINVAL;
memset(&v, 0, sizeof(v));
switch (optname) {
case SO_DEBUG:
v.val = sock_flag(sk, SOCK_DBG);
break;
case SO_DONTROUTE:
v.val = sock_flag(sk, SOCK_LOCALROUTE);
break;
case SO_BROADCAST:
v.val = sock_flag(sk, SOCK_BROADCAST);
break;
case SO_SNDBUF:
v.val = sk->sk_sndbuf;
break;
case SO_RCVBUF:
v.val = sk->sk_rcvbuf;
break;
case SO_REUSEADDR:
v.val = sk->sk_reuse;
break;
case SO_REUSEPORT:
v.val = sk->sk_reuseport;
break;
case SO_KEEPALIVE:
v.val = sock_flag(sk, SOCK_KEEPOPEN);
break;
case SO_TYPE:
v.val = sk->sk_type;
break;
case SO_PROTOCOL:
v.val = sk->sk_protocol;
break;
case SO_DOMAIN:
v.val = sk->sk_family;
break;
case SO_ERROR:
v.val = -sock_error(sk);
if (v.val == 0)
v.val = xchg(&sk->sk_err_soft, 0);
break;
case SO_OOBINLINE:
v.val = sock_flag(sk, SOCK_URGINLINE);
break;
case SO_NO_CHECK:
v.val = sk->sk_no_check_tx;
break;
case SO_PRIORITY:
v.val = sk->sk_priority;
break;
case SO_LINGER:
lv = sizeof(v.ling);
v.ling.l_onoff = sock_flag(sk, SOCK_LINGER);
v.ling.l_linger = sk->sk_lingertime / HZ;
break;
case SO_BSDCOMPAT:
break;
case SO_TIMESTAMP_OLD:
v.val = sock_flag(sk, SOCK_RCVTSTAMP) &&
!sock_flag(sk, SOCK_TSTAMP_NEW) &&
!sock_flag(sk, SOCK_RCVTSTAMPNS);
break;
case SO_TIMESTAMPNS_OLD:
v.val = sock_flag(sk, SOCK_RCVTSTAMPNS) && !sock_flag(sk, SOCK_TSTAMP_NEW);
break;
case SO_TIMESTAMP_NEW:
v.val = sock_flag(sk, SOCK_RCVTSTAMP) && sock_flag(sk, SOCK_TSTAMP_NEW);
break;
case SO_TIMESTAMPNS_NEW:
v.val = sock_flag(sk, SOCK_RCVTSTAMPNS) && sock_flag(sk, SOCK_TSTAMP_NEW);
break;
case SO_TIMESTAMPING_OLD:
v.val = sk->sk_tsflags;
break;
case SO_RCVTIMEO_OLD:
case SO_RCVTIMEO_NEW:
lv = sock_get_timeout(sk->sk_rcvtimeo, &v, SO_RCVTIMEO_OLD == optname);
break;
case SO_SNDTIMEO_OLD:
case SO_SNDTIMEO_NEW:
lv = sock_get_timeout(sk->sk_sndtimeo, &v, SO_SNDTIMEO_OLD == optname);
break;
case SO_RCVLOWAT:
v.val = sk->sk_rcvlowat;
break;
case SO_SNDLOWAT:
v.val = 1;
break;
case SO_PASSCRED:
v.val = !!test_bit(SOCK_PASSCRED, &sock->flags);
break;
case SO_PEERCRED:
{
struct ucred peercred;
if (len > sizeof(peercred))
len = sizeof(peercred);
cred_to_ucred(sk->sk_peer_pid, sk->sk_peer_cred, &peercred);
if (copy_to_user(optval, &peercred, len))
return -EFAULT;
goto lenout;
}
net: introduce SO_PEERGROUPS getsockopt This adds the new getsockopt(2) option SO_PEERGROUPS on SOL_SOCKET to retrieve the auxiliary groups of the remote peer. It is designed to naturally extend SO_PEERCRED. That is, the underlying data is from the same credentials. Regarding its syntax, it is based on SO_PEERSEC. That is, if the provided buffer is too small, ERANGE is returned and @optlen is updated. Otherwise, the information is copied, @optlen is set to the actual size, and 0 is returned. While SO_PEERCRED (and thus `struct ucred') already returns the primary group, it lacks the auxiliary group vector. However, nearly all access controls (including kernel side VFS and SYSVIPC, but also user-space polkit, DBus, ...) consider the entire set of groups, rather than just the primary group. But this is currently not possible with pure SO_PEERCRED. Instead, user-space has to work around this and query the system database for the auxiliary groups of a UID retrieved via SO_PEERCRED. Unfortunately, there is no race-free way to query the auxiliary groups of the PID/UID retrieved via SO_PEERCRED. Hence, the current user-space solution is to use getgrouplist(3p), which itself falls back to NSS and whatever is configured in nsswitch.conf(3). This effectively checks which groups we *would* assign to the user if it logged in *now*. On normal systems it is as easy as reading /etc/group, but with NSS it can resort to quering network databases (eg., LDAP), using IPC or network communication. Long story short: Whenever we want to use auxiliary groups for access checks on IPC, we need further IPC to talk to the user/group databases, rather than just relying on SO_PEERCRED and the incoming socket. This is unfortunate, and might even result in dead-locks if the database query uses the same IPC as the original request. So far, those recursions / dead-locks have been avoided by using primitive IPC for all crucial NSS modules. However, we want to avoid re-inventing the wheel for each NSS module that might be involved in user/group queries. Hence, we would preferably make DBus (and other IPC that supports access-management based on groups) work without resorting to the user/group database. This new SO_PEERGROUPS ioctl would allow us to make dbus-daemon work without ever calling into NSS. Cc: Michal Sekletar <msekleta@redhat.com> Cc: Simon McVittie <simon.mcvittie@collabora.co.uk> Reviewed-by: Tom Gundersen <teg@jklm.no> Signed-off-by: David Herrmann <dh.herrmann@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-06-21 08:47:15 +00:00
case SO_PEERGROUPS:
{
int ret, n;
if (!sk->sk_peer_cred)
return -ENODATA;
n = sk->sk_peer_cred->group_info->ngroups;
if (len < n * sizeof(gid_t)) {
len = n * sizeof(gid_t);
return put_user(len, optlen) ? -EFAULT : -ERANGE;
}
len = n * sizeof(gid_t);
ret = groups_to_user((gid_t __user *)optval,
sk->sk_peer_cred->group_info);
if (ret)
return ret;
goto lenout;
}
case SO_PEERNAME:
{
char address[128];
net: make getname() functions return length rather than use int* parameter Changes since v1: Added changes in these files: drivers/infiniband/hw/usnic/usnic_transport.c drivers/staging/lustre/lnet/lnet/lib-socket.c drivers/target/iscsi/iscsi_target_login.c drivers/vhost/net.c fs/dlm/lowcomms.c fs/ocfs2/cluster/tcp.c security/tomoyo/network.c Before: All these functions either return a negative error indicator, or store length of sockaddr into "int *socklen" parameter and return zero on success. "int *socklen" parameter is awkward. For example, if caller does not care, it still needs to provide on-stack storage for the value it does not need. None of the many FOO_getname() functions of various protocols ever used old value of *socklen. They always just overwrite it. This change drops this parameter, and makes all these functions, on success, return length of sockaddr. It's always >= 0 and can be differentiated from an error. Tests in callers are changed from "if (err)" to "if (err < 0)", where needed. rpc_sockname() lost "int buflen" parameter, since its only use was to be passed to kernel_getsockname() as &buflen and subsequently not used in any way. Userspace API is not changed. text data bss dec hex filename 30108430 2633624 873672 33615726 200ef6e vmlinux.before.o 30108109 2633612 873672 33615393 200ee21 vmlinux.o Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com> CC: David S. Miller <davem@davemloft.net> CC: linux-kernel@vger.kernel.org CC: netdev@vger.kernel.org CC: linux-bluetooth@vger.kernel.org CC: linux-decnet-user@lists.sourceforge.net CC: linux-wireless@vger.kernel.org CC: linux-rdma@vger.kernel.org CC: linux-sctp@vger.kernel.org CC: linux-nfs@vger.kernel.org CC: linux-x25@vger.kernel.org Signed-off-by: David S. Miller <davem@davemloft.net>
2018-02-12 19:00:20 +00:00
lv = sock->ops->getname(sock, (struct sockaddr *)address, 2);
if (lv < 0)
return -ENOTCONN;
if (lv < len)
return -EINVAL;
if (copy_to_user(optval, address, len))
return -EFAULT;
goto lenout;
}
/* Dubious BSD thing... Probably nobody even uses it, but
* the UNIX standard wants it for whatever reason... -DaveM
*/
case SO_ACCEPTCONN:
v.val = sk->sk_state == TCP_LISTEN;
break;
case SO_PASSSEC:
v.val = !!test_bit(SOCK_PASSSEC, &sock->flags);
break;
[AF_UNIX]: Datagram getpeersec This patch implements an API whereby an application can determine the label of its peer's Unix datagram sockets via the auxiliary data mechanism of recvmsg. Patch purpose: This patch enables a security-aware application to retrieve the security context of the peer of a Unix datagram socket. The application can then use this security context to determine the security context for processing on behalf of the peer who sent the packet. Patch design and implementation: The design and implementation is very similar to the UDP case for INET sockets. Basically we build upon the existing Unix domain socket API for retrieving user credentials. Linux offers the API for obtaining user credentials via ancillary messages (i.e., out of band/control messages that are bundled together with a normal message). To retrieve the security context, the application first indicates to the kernel such desire by setting the SO_PASSSEC option via getsockopt. Then the application retrieves the security context using the auxiliary data mechanism. An example server application for Unix datagram socket should look like this: toggle = 1; toggle_len = sizeof(toggle); setsockopt(sockfd, SOL_SOCKET, SO_PASSSEC, &toggle, &toggle_len); recvmsg(sockfd, &msg_hdr, 0); if (msg_hdr.msg_controllen > sizeof(struct cmsghdr)) { cmsg_hdr = CMSG_FIRSTHDR(&msg_hdr); if (cmsg_hdr->cmsg_len <= CMSG_LEN(sizeof(scontext)) && cmsg_hdr->cmsg_level == SOL_SOCKET && cmsg_hdr->cmsg_type == SCM_SECURITY) { memcpy(&scontext, CMSG_DATA(cmsg_hdr), sizeof(scontext)); } } sock_setsockopt is enhanced with a new socket option SOCK_PASSSEC to allow a server socket to receive security context of the peer. Testing: We have tested the patch by setting up Unix datagram client and server applications. We verified that the server can retrieve the security context using the auxiliary data mechanism of recvmsg. Signed-off-by: Catherine Zhang <cxzhang@watson.ibm.com> Acked-by: Acked-by: James Morris <jmorris@namei.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-29 19:27:47 +00:00
case SO_PEERSEC:
return security_socket_getpeersec_stream(sock, optval, optlen, len);
case SO_MARK:
v.val = sk->sk_mark;
break;
net: Generalize socket rx gap / receive queue overflow cmsg Create a new socket level option to report number of queue overflows Recently I augmented the AF_PACKET protocol to report the number of frames lost on the socket receive queue between any two enqueued frames. This value was exported via a SOL_PACKET level cmsg. AFter I completed that work it was requested that this feature be generalized so that any datagram oriented socket could make use of this option. As such I've created this patch, It creates a new SOL_SOCKET level option called SO_RXQ_OVFL, which when enabled exports a SOL_SOCKET level cmsg that reports the nubmer of times the sk_receive_queue overflowed between any two given frames. It also augments the AF_PACKET protocol to take advantage of this new feature (as it previously did not touch sk->sk_drops, which this patch uses to record the overflow count). Tested successfully by me. Notes: 1) Unlike my previous patch, this patch simply records the sk_drops value, which is not a number of drops between packets, but rather a total number of drops. Deltas must be computed in user space. 2) While this patch currently works with datagram oriented protocols, it will also be accepted by non-datagram oriented protocols. I'm not sure if thats agreeable to everyone, but my argument in favor of doing so is that, for those protocols which aren't applicable to this option, sk_drops will always be zero, and reporting no drops on a receive queue that isn't used for those non-participating protocols seems reasonable to me. This also saves us having to code in a per-protocol opt in mechanism. 3) This applies cleanly to net-next assuming that commit 977750076d98c7ff6cbda51858bb5a5894a9d9ab (my af packet cmsg patch) is reverted Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-10-12 20:26:31 +00:00
case SO_RXQ_OVFL:
v.val = sock_flag(sk, SOCK_RXQ_OVFL);
net: Generalize socket rx gap / receive queue overflow cmsg Create a new socket level option to report number of queue overflows Recently I augmented the AF_PACKET protocol to report the number of frames lost on the socket receive queue between any two enqueued frames. This value was exported via a SOL_PACKET level cmsg. AFter I completed that work it was requested that this feature be generalized so that any datagram oriented socket could make use of this option. As such I've created this patch, It creates a new SOL_SOCKET level option called SO_RXQ_OVFL, which when enabled exports a SOL_SOCKET level cmsg that reports the nubmer of times the sk_receive_queue overflowed between any two given frames. It also augments the AF_PACKET protocol to take advantage of this new feature (as it previously did not touch sk->sk_drops, which this patch uses to record the overflow count). Tested successfully by me. Notes: 1) Unlike my previous patch, this patch simply records the sk_drops value, which is not a number of drops between packets, but rather a total number of drops. Deltas must be computed in user space. 2) While this patch currently works with datagram oriented protocols, it will also be accepted by non-datagram oriented protocols. I'm not sure if thats agreeable to everyone, but my argument in favor of doing so is that, for those protocols which aren't applicable to this option, sk_drops will always be zero, and reporting no drops on a receive queue that isn't used for those non-participating protocols seems reasonable to me. This also saves us having to code in a per-protocol opt in mechanism. 3) This applies cleanly to net-next assuming that commit 977750076d98c7ff6cbda51858bb5a5894a9d9ab (my af packet cmsg patch) is reverted Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-10-12 20:26:31 +00:00
break;
case SO_WIFI_STATUS:
v.val = sock_flag(sk, SOCK_WIFI_STATUS);
break;
case SO_PEEK_OFF:
if (!sock->ops->set_peek_off)
return -EOPNOTSUPP;
v.val = sk->sk_peek_off;
break;
case SO_NOFCS:
v.val = sock_flag(sk, SOCK_NOFCS);
break;
case SO_BINDTODEVICE:
return sock_getbindtodevice(sk, optval, optlen, len);
sk-filter: Add ability to get socket filter program (v2) The SO_ATTACH_FILTER option is set only. I propose to add the get ability by using SO_ATTACH_FILTER in getsockopt. To be less irritating to eyes the SO_GET_FILTER alias to it is declared. This ability is required by checkpoint-restore project to be able to save full state of a socket. There are two issues with getting filter back. First, kernel modifies the sock_filter->code on filter load, thus in order to return the filter element back to user we have to decode it into user-visible constants. Fortunately the modification in question is interconvertible. Second, the BPF_S_ALU_DIV_K code modifies the command argument k to speed up the run-time division by doing kernel_k = reciprocal(user_k). Bad news is that different user_k may result in same kernel_k, so we can't get the original user_k back. Good news is that we don't have to do it. What we need to is calculate a user2_k so, that reciprocal(user2_k) == reciprocal(user_k) == kernel_k i.e. if it's re-loaded back the compiled again value will be exactly the same as it was. That said, the user2_k can be calculated like this user2_k = reciprocal(kernel_k) with an exception, that if kernel_k == 0, then user2_k == 1. The optlen argument is treated like this -- when zero, kernel returns the amount of sock_fprog elements in filter, otherwise it should be large enough for the sock_fprog array. changes since v1: * Declared SO_GET_FILTER in all arch headers * Added decode of vlan-tag codes Signed-off-by: Pavel Emelyanov <xemul@parallels.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-11-01 02:01:48 +00:00
case SO_GET_FILTER:
len = sk_get_filter(sk, (struct sock_filter __user *)optval, len);
if (len < 0)
return len;
goto lenout;
case SO_LOCK_FILTER:
v.val = sock_flag(sk, SOCK_FILTER_LOCKED);
break;
case SO_BPF_EXTENSIONS:
v.val = bpf_tell_extensions();
break;
case SO_SELECT_ERR_QUEUE:
v.val = sock_flag(sk, SOCK_SELECT_ERR_QUEUE);
break;
#ifdef CONFIG_NET_RX_BUSY_POLL
case SO_BUSY_POLL:
v.val = sk->sk_ll_usec;
break;
net: Introduce preferred busy-polling The existing busy-polling mode, enabled by the SO_BUSY_POLL socket option or system-wide using the /proc/sys/net/core/busy_read knob, is an opportunistic. That means that if the NAPI context is not scheduled, it will poll it. If, after busy-polling, the budget is exceeded the busy-polling logic will schedule the NAPI onto the regular softirq handling. One implication of the behavior above is that a busy/heavy loaded NAPI context will never enter/allow for busy-polling. Some applications prefer that most NAPI processing would be done by busy-polling. This series adds a new socket option, SO_PREFER_BUSY_POLL, that works in concert with the napi_defer_hard_irqs and gro_flush_timeout knobs. The napi_defer_hard_irqs and gro_flush_timeout knobs were introduced in commit 6f8b12d661d0 ("net: napi: add hard irqs deferral feature"), and allows for a user to defer interrupts to be enabled and instead schedule the NAPI context from a watchdog timer. When a user enables the SO_PREFER_BUSY_POLL, again with the other knobs enabled, and the NAPI context is being processed by a softirq, the softirq NAPI processing will exit early to allow the busy-polling to be performed. If the application stops performing busy-polling via a system call, the watchdog timer defined by gro_flush_timeout will timeout, and regular softirq handling will resume. In summary; Heavy traffic applications that prefer busy-polling over softirq processing should use this option. Example usage: $ echo 2 | sudo tee /sys/class/net/ens785f1/napi_defer_hard_irqs $ echo 200000 | sudo tee /sys/class/net/ens785f1/gro_flush_timeout Note that the timeout should be larger than the userspace processing window, otherwise the watchdog will timeout and fall back to regular softirq processing. Enable the SO_BUSY_POLL/SO_PREFER_BUSY_POLL options on your socket. Signed-off-by: Björn Töpel <bjorn.topel@intel.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Jakub Kicinski <kuba@kernel.org> Link: https://lore.kernel.org/bpf/20201130185205.196029-2-bjorn.topel@gmail.com
2020-11-30 18:51:56 +00:00
case SO_PREFER_BUSY_POLL:
v.val = READ_ONCE(sk->sk_prefer_busy_poll);
break;
#endif
case SO_MAX_PACING_RATE:
if (sizeof(v.ulval) != sizeof(v.val) && len >= sizeof(v.ulval)) {
lv = sizeof(v.ulval);
v.ulval = sk->sk_max_pacing_rate;
} else {
/* 32bit version */
v.val = min_t(unsigned long, sk->sk_max_pacing_rate, ~0U);
}
break;
case SO_INCOMING_CPU:
net: annotate accesses to sk->sk_incoming_cpu This socket field can be read and written by concurrent cpus. Use READ_ONCE() and WRITE_ONCE() annotations to document this, and avoid some compiler 'optimizations'. KCSAN reported : BUG: KCSAN: data-race in tcp_v4_rcv / tcp_v4_rcv write to 0xffff88812220763c of 4 bytes by interrupt on cpu 0: sk_incoming_cpu_update include/net/sock.h:953 [inline] tcp_v4_rcv+0x1b3c/0x1bb0 net/ipv4/tcp_ipv4.c:1934 ip_protocol_deliver_rcu+0x4d/0x420 net/ipv4/ip_input.c:204 ip_local_deliver_finish+0x110/0x140 net/ipv4/ip_input.c:231 NF_HOOK include/linux/netfilter.h:305 [inline] NF_HOOK include/linux/netfilter.h:299 [inline] ip_local_deliver+0x133/0x210 net/ipv4/ip_input.c:252 dst_input include/net/dst.h:442 [inline] ip_rcv_finish+0x121/0x160 net/ipv4/ip_input.c:413 NF_HOOK include/linux/netfilter.h:305 [inline] NF_HOOK include/linux/netfilter.h:299 [inline] ip_rcv+0x18f/0x1a0 net/ipv4/ip_input.c:523 __netif_receive_skb_one_core+0xa7/0xe0 net/core/dev.c:5010 __netif_receive_skb+0x37/0xf0 net/core/dev.c:5124 process_backlog+0x1d3/0x420 net/core/dev.c:5955 napi_poll net/core/dev.c:6392 [inline] net_rx_action+0x3ae/0xa90 net/core/dev.c:6460 __do_softirq+0x115/0x33f kernel/softirq.c:292 do_softirq_own_stack+0x2a/0x40 arch/x86/entry/entry_64.S:1082 do_softirq.part.0+0x6b/0x80 kernel/softirq.c:337 do_softirq kernel/softirq.c:329 [inline] __local_bh_enable_ip+0x76/0x80 kernel/softirq.c:189 read to 0xffff88812220763c of 4 bytes by interrupt on cpu 1: sk_incoming_cpu_update include/net/sock.h:952 [inline] tcp_v4_rcv+0x181a/0x1bb0 net/ipv4/tcp_ipv4.c:1934 ip_protocol_deliver_rcu+0x4d/0x420 net/ipv4/ip_input.c:204 ip_local_deliver_finish+0x110/0x140 net/ipv4/ip_input.c:231 NF_HOOK include/linux/netfilter.h:305 [inline] NF_HOOK include/linux/netfilter.h:299 [inline] ip_local_deliver+0x133/0x210 net/ipv4/ip_input.c:252 dst_input include/net/dst.h:442 [inline] ip_rcv_finish+0x121/0x160 net/ipv4/ip_input.c:413 NF_HOOK include/linux/netfilter.h:305 [inline] NF_HOOK include/linux/netfilter.h:299 [inline] ip_rcv+0x18f/0x1a0 net/ipv4/ip_input.c:523 __netif_receive_skb_one_core+0xa7/0xe0 net/core/dev.c:5010 __netif_receive_skb+0x37/0xf0 net/core/dev.c:5124 process_backlog+0x1d3/0x420 net/core/dev.c:5955 napi_poll net/core/dev.c:6392 [inline] net_rx_action+0x3ae/0xa90 net/core/dev.c:6460 __do_softirq+0x115/0x33f kernel/softirq.c:292 run_ksoftirqd+0x46/0x60 kernel/softirq.c:603 smpboot_thread_fn+0x37d/0x4a0 kernel/smpboot.c:165 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 16 Comm: ksoftirqd/1 Not tainted 5.4.0-rc3+ #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-10-30 20:00:04 +00:00
v.val = READ_ONCE(sk->sk_incoming_cpu);
break;
case SO_MEMINFO:
{
u32 meminfo[SK_MEMINFO_VARS];
sk_get_meminfo(sk, meminfo);
len = min_t(unsigned int, len, sizeof(meminfo));
if (copy_to_user(optval, &meminfo, len))
return -EFAULT;
goto lenout;
}
#ifdef CONFIG_NET_RX_BUSY_POLL
case SO_INCOMING_NAPI_ID:
v.val = READ_ONCE(sk->sk_napi_id);
/* aggregate non-NAPI IDs down to 0 */
if (v.val < MIN_NAPI_ID)
v.val = 0;
break;
#endif
case SO_COOKIE:
lv = sizeof(u64);
if (len < lv)
return -EINVAL;
v.val64 = sock_gen_cookie(sk);
break;
case SO_ZEROCOPY:
v.val = sock_flag(sk, SOCK_ZEROCOPY);
break;
case SO_TXTIME:
lv = sizeof(v.txtime);
v.txtime.clockid = sk->sk_clockid;
v.txtime.flags |= sk->sk_txtime_deadline_mode ?
SOF_TXTIME_DEADLINE_MODE : 0;
v.txtime.flags |= sk->sk_txtime_report_errors ?
SOF_TXTIME_REPORT_ERRORS : 0;
break;
net: introduce SO_BINDTOIFINDEX sockopt This introduces a new generic SOL_SOCKET-level socket option called SO_BINDTOIFINDEX. It behaves similar to SO_BINDTODEVICE, but takes a network interface index as argument, rather than the network interface name. User-space often refers to network-interfaces via their index, but has to temporarily resolve it to a name for a call into SO_BINDTODEVICE. This might pose problems when the network-device is renamed asynchronously by other parts of the system. When this happens, the SO_BINDTODEVICE might either fail, or worse, it might bind to the wrong device. In most cases user-space only ever operates on devices which they either manage themselves, or otherwise have a guarantee that the device name will not change (e.g., devices that are UP cannot be renamed). However, particularly in libraries this guarantee is non-obvious and it would be nice if that race-condition would simply not exist. It would make it easier for those libraries to operate even in situations where the device-name might change under the hood. A real use-case that we recently hit is trying to start the network stack early in the initrd but make it survive into the real system. Existing distributions rename network-interfaces during the transition from initrd into the real system. This, obviously, cannot affect devices that are up and running (unless you also consider moving them between network-namespaces). However, the network manager now has to make sure its management engine for dormant devices will not run in parallel to these renames. Particularly, when you offload operations like DHCP into separate processes, these might setup their sockets early, and thus have to resolve the device-name possibly running into this race-condition. By avoiding a call to resolve the device-name, we no longer depend on the name and can run network setup of dormant devices in parallel to the transition off the initrd. The SO_BINDTOIFINDEX ioctl plugs this race. Reviewed-by: Tom Gundersen <teg@jklm.no> Signed-off-by: David Herrmann <dh.herrmann@gmail.com> Acked-by: Willem de Bruijn <willemb@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-01-15 13:42:14 +00:00
case SO_BINDTOIFINDEX:
v.val = sk->sk_bound_dev_if;
break;
default:
/* We implement the SO_SNDLOWAT etc to not be settable
* (1003.1g 7).
*/
return -ENOPROTOOPT;
}
if (len > lv)
len = lv;
if (copy_to_user(optval, &v, len))
return -EFAULT;
lenout:
if (put_user(len, optlen))
return -EFAULT;
return 0;
}
/*
* Initialize an sk_lock.
*
* (We also register the sk_lock with the lock validator.)
*/
static inline void sock_lock_init(struct sock *sk)
{
net: Work around lockdep limitation in sockets that use sockets Lockdep issues a circular dependency warning when AFS issues an operation through AF_RXRPC from a context in which the VFS/VM holds the mmap_sem. The theory lockdep comes up with is as follows: (1) If the pagefault handler decides it needs to read pages from AFS, it calls AFS with mmap_sem held and AFS begins an AF_RXRPC call, but creating a call requires the socket lock: mmap_sem must be taken before sk_lock-AF_RXRPC (2) afs_open_socket() opens an AF_RXRPC socket and binds it. rxrpc_bind() binds the underlying UDP socket whilst holding its socket lock. inet_bind() takes its own socket lock: sk_lock-AF_RXRPC must be taken before sk_lock-AF_INET (3) Reading from a TCP socket into a userspace buffer might cause a fault and thus cause the kernel to take the mmap_sem, but the TCP socket is locked whilst doing this: sk_lock-AF_INET must be taken before mmap_sem However, lockdep's theory is wrong in this instance because it deals only with lock classes and not individual locks. The AF_INET lock in (2) isn't really equivalent to the AF_INET lock in (3) as the former deals with a socket entirely internal to the kernel that never sees userspace. This is a limitation in the design of lockdep. Fix the general case by: (1) Double up all the locking keys used in sockets so that one set are used if the socket is created by userspace and the other set is used if the socket is created by the kernel. (2) Store the kern parameter passed to sk_alloc() in a variable in the sock struct (sk_kern_sock). This informs sock_lock_init(), sock_init_data() and sk_clone_lock() as to the lock keys to be used. Note that the child created by sk_clone_lock() inherits the parent's kern setting. (3) Add a 'kern' parameter to ->accept() that is analogous to the one passed in to ->create() that distinguishes whether kernel_accept() or sys_accept4() was the caller and can be passed to sk_alloc(). Note that a lot of accept functions merely dequeue an already allocated socket. I haven't touched these as the new socket already exists before we get the parameter. Note also that there are a couple of places where I've made the accepted socket unconditionally kernel-based: irda_accept() rds_rcp_accept_one() tcp_accept_from_sock() because they follow a sock_create_kern() and accept off of that. Whilst creating this, I noticed that lustre and ocfs don't create sockets through sock_create_kern() and thus they aren't marked as for-kernel, though they appear to be internal. I wonder if these should do that so that they use the new set of lock keys. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-09 08:09:05 +00:00
if (sk->sk_kern_sock)
sock_lock_init_class_and_name(
sk,
af_family_kern_slock_key_strings[sk->sk_family],
af_family_kern_slock_keys + sk->sk_family,
af_family_kern_key_strings[sk->sk_family],
af_family_kern_keys + sk->sk_family);
else
sock_lock_init_class_and_name(
sk,
af_family_slock_key_strings[sk->sk_family],
af_family_slock_keys + sk->sk_family,
af_family_key_strings[sk->sk_family],
af_family_keys + sk->sk_family);
}
/*
* Copy all fields from osk to nsk but nsk->sk_refcnt must not change yet,
* even temporarly, because of RCU lookups. sk_node should also be left as is.
* We must not copy fields between sk_dontcopy_begin and sk_dontcopy_end
*/
static void sock_copy(struct sock *nsk, const struct sock *osk)
{
const struct proto *prot = READ_ONCE(osk->sk_prot);
#ifdef CONFIG_SECURITY_NETWORK
void *sptr = nsk->sk_security;
#endif
/* If we move sk_tx_queue_mapping out of the private section,
* we must check if sk_tx_queue_clear() is called after
* sock_copy() in sk_clone_lock().
*/
BUILD_BUG_ON(offsetof(struct sock, sk_tx_queue_mapping) <
offsetof(struct sock, sk_dontcopy_begin) ||
offsetof(struct sock, sk_tx_queue_mapping) >=
offsetof(struct sock, sk_dontcopy_end));
memcpy(nsk, osk, offsetof(struct sock, sk_dontcopy_begin));
memcpy(&nsk->sk_dontcopy_end, &osk->sk_dontcopy_end,
prot->obj_size - offsetof(struct sock, sk_dontcopy_end));
#ifdef CONFIG_SECURITY_NETWORK
nsk->sk_security = sptr;
security_sk_clone(osk, nsk);
#endif
}
static struct sock *sk_prot_alloc(struct proto *prot, gfp_t priority,
int family)
{
struct sock *sk;
struct kmem_cache *slab;
slab = prot->slab;
if (slab != NULL) {
sk = kmem_cache_alloc(slab, priority & ~__GFP_ZERO);
if (!sk)
return sk;
mm: security: introduce init_on_alloc=1 and init_on_free=1 boot options Patch series "add init_on_alloc/init_on_free boot options", v10. Provide init_on_alloc and init_on_free boot options. These are aimed at preventing possible information leaks and making the control-flow bugs that depend on uninitialized values more deterministic. Enabling either of the options guarantees that the memory returned by the page allocator and SL[AU]B is initialized with zeroes. SLOB allocator isn't supported at the moment, as its emulation of kmem caches complicates handling of SLAB_TYPESAFE_BY_RCU caches correctly. Enabling init_on_free also guarantees that pages and heap objects are initialized right after they're freed, so it won't be possible to access stale data by using a dangling pointer. As suggested by Michal Hocko, right now we don't let the heap users to disable initialization for certain allocations. There's not enough evidence that doing so can speed up real-life cases, and introducing ways to opt-out may result in things going out of control. This patch (of 2): The new options are needed to prevent possible information leaks and make control-flow bugs that depend on uninitialized values more deterministic. This is expected to be on-by-default on Android and Chrome OS. And it gives the opportunity for anyone else to use it under distros too via the boot args. (The init_on_free feature is regularly requested by folks where memory forensics is included in their threat models.) init_on_alloc=1 makes the kernel initialize newly allocated pages and heap objects with zeroes. Initialization is done at allocation time at the places where checks for __GFP_ZERO are performed. init_on_free=1 makes the kernel initialize freed pages and heap objects with zeroes upon their deletion. This helps to ensure sensitive data doesn't leak via use-after-free accesses. Both init_on_alloc=1 and init_on_free=1 guarantee that the allocator returns zeroed memory. The two exceptions are slab caches with constructors and SLAB_TYPESAFE_BY_RCU flag. Those are never zero-initialized to preserve their semantics. Both init_on_alloc and init_on_free default to zero, but those defaults can be overridden with CONFIG_INIT_ON_ALLOC_DEFAULT_ON and CONFIG_INIT_ON_FREE_DEFAULT_ON. If either SLUB poisoning or page poisoning is enabled, those options take precedence over init_on_alloc and init_on_free: initialization is only applied to unpoisoned allocations. Slowdown for the new features compared to init_on_free=0, init_on_alloc=0: hackbench, init_on_free=1: +7.62% sys time (st.err 0.74%) hackbench, init_on_alloc=1: +7.75% sys time (st.err 2.14%) Linux build with -j12, init_on_free=1: +8.38% wall time (st.err 0.39%) Linux build with -j12, init_on_free=1: +24.42% sys time (st.err 0.52%) Linux build with -j12, init_on_alloc=1: -0.13% wall time (st.err 0.42%) Linux build with -j12, init_on_alloc=1: +0.57% sys time (st.err 0.40%) The slowdown for init_on_free=0, init_on_alloc=0 compared to the baseline is within the standard error. The new features are also going to pave the way for hardware memory tagging (e.g. arm64's MTE), which will require both on_alloc and on_free hooks to set the tags for heap objects. With MTE, tagging will have the same cost as memory initialization. Although init_on_free is rather costly, there are paranoid use-cases where in-memory data lifetime is desired to be minimized. There are various arguments for/against the realism of the associated threat models, but given that we'll need the infrastructure for MTE anyway, and there are people who want wipe-on-free behavior no matter what the performance cost, it seems reasonable to include it in this series. [glider@google.com: v8] Link: http://lkml.kernel.org/r/20190626121943.131390-2-glider@google.com [glider@google.com: v9] Link: http://lkml.kernel.org/r/20190627130316.254309-2-glider@google.com [glider@google.com: v10] Link: http://lkml.kernel.org/r/20190628093131.199499-2-glider@google.com Link: http://lkml.kernel.org/r/20190617151050.92663-2-glider@google.com Signed-off-by: Alexander Potapenko <glider@google.com> Acked-by: Kees Cook <keescook@chromium.org> Acked-by: Michal Hocko <mhocko@suse.cz> [page and dmapool parts Acked-by: James Morris <jamorris@linux.microsoft.com>] Cc: Christoph Lameter <cl@linux.com> Cc: Masahiro Yamada <yamada.masahiro@socionext.com> Cc: "Serge E. Hallyn" <serge@hallyn.com> Cc: Nick Desaulniers <ndesaulniers@google.com> Cc: Kostya Serebryany <kcc@google.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Sandeep Patil <sspatil@android.com> Cc: Laura Abbott <labbott@redhat.com> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Jann Horn <jannh@google.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Marco Elver <elver@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-12 03:59:19 +00:00
if (want_init_on_alloc(priority))
sk_prot_clear_nulls(sk, prot->obj_size);
} else
sk = kmalloc(prot->obj_size, priority);
if (sk != NULL) {
if (security_sk_alloc(sk, family, priority))
goto out_free;
if (!try_module_get(prot->owner))
goto out_free_sec;
}
return sk;
out_free_sec:
security_sk_free(sk);
out_free:
if (slab != NULL)
kmem_cache_free(slab, sk);
else
kfree(sk);
return NULL;
}
static void sk_prot_free(struct proto *prot, struct sock *sk)
{
struct kmem_cache *slab;
struct module *owner;
owner = prot->owner;
slab = prot->slab;
sock, cgroup: add sock->sk_cgroup In cgroup v1, dealing with cgroup membership was difficult because the number of membership associations was unbound. As a result, cgroup v1 grew several controllers whose primary purpose is either tagging membership or pull in configuration knobs from other subsystems so that cgroup membership test can be avoided. net_cls and net_prio controllers are examples of the latter. They allow configuring network-specific attributes from cgroup side so that network subsystem can avoid testing cgroup membership; unfortunately, these are not only cumbersome but also problematic. Both net_cls and net_prio aren't properly hierarchical. Both inherit configuration from the parent on creation but there's no interaction afterwards. An ancestor doesn't restrict the behavior in its subtree in anyway and configuration changes aren't propagated downwards. Especially when combined with cgroup delegation, this is problematic because delegatees can mess up whatever network configuration implemented at the system level. net_prio would allow the delegatees to set whatever priority value regardless of CAP_NET_ADMIN and net_cls the same for classid. While it is possible to solve these issues from controller side by implementing hierarchical allowable ranges in both controllers, it would involve quite a bit of complexity in the controllers and further obfuscate network configuration as it becomes even more difficult to tell what's actually being configured looking from the network side. While not much can be done for v1 at this point, as membership handling is sane on cgroup v2, it'd be better to make cgroup matching behave like other network matches and classifiers than introducing further complications. In preparation, this patch updates sock->sk_cgrp_data handling so that it points to the v2 cgroup that sock was created in until either net_prio or net_cls is used. Once either of the two is used, sock->sk_cgrp_data reverts to its previous role of carrying prioidx and classid. This is to avoid adding yet another cgroup related field to struct sock. As the mode switching can happen at most once per boot, the switching mechanism is aimed at lowering hot path overhead. It may leak a finite, likely small, number of cgroup refs and report spurious prioidx or classid on switching; however, dynamic updates of prioidx and classid have always been racy and lossy - socks between creation and fd installation are never updated, config changes don't update existing sockets at all, and prioidx may index with dead and recycled cgroup IDs. Non-critical inaccuracies from small race windows won't make any noticeable difference. This patch doesn't make use of the pointer yet. The following patch will implement netfilter match for cgroup2 membership. v2: Use sock_cgroup_data to avoid inflating struct sock w/ another cgroup specific field. v3: Add comments explaining why sock_data_prioidx() and sock_data_classid() use different fallback values. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Daniel Wagner <daniel.wagner@bmw-carit.de> CC: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-12-07 22:38:53 +00:00
cgroup_sk_free(&sk->sk_cgrp_data);
mem_cgroup_sk_free(sk);
security_sk_free(sk);
if (slab != NULL)
kmem_cache_free(slab, sk);
else
kfree(sk);
module_put(owner);
}
/**
* sk_alloc - All socket objects are allocated here
* @net: the applicable net namespace
[PATCH] DocBook: changes and extensions to the kernel documentation I have recompiled Linux kernel 2.6.11.5 documentation for me and our university students again. The documentation could be extended for more sources which are equipped by structured comments for recent 2.6 kernels. I have tried to proceed with that task. I have done that more times from 2.6.0 time and it gets boring to do same changes again and again. Linux kernel compiles after changes for i386 and ARM targets. I have added references to some more files into kernel-api book, I have added some section names as well. So please, check that changes do not break something and that categories are not too much skewed. I have changed kernel-doc to accept "fastcall" and "asmlinkage" words reserved by kernel convention. Most of the other changes are modifications in the comments to make kernel-doc happy, accept some parameters description and do not bail out on errors. Changed <pid> to @pid in the description, moved some #ifdef before comments to correct function to comments bindings, etc. You can see result of the modified documentation build at http://cmp.felk.cvut.cz/~pisa/linux/lkdb-2.6.11.tar.gz Some more sources are ready to be included into kernel-doc generated documentation. Sources has been added into kernel-api for now. Some more section names added and probably some more chaos introduced as result of quick cleanup work. Signed-off-by: Pavel Pisa <pisa@cmp.felk.cvut.cz> Signed-off-by: Martin Waitz <tali@admingilde.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-05-01 15:59:25 +00:00
* @family: protocol family
* @priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc)
* @prot: struct proto associated with this new sock instance
* @kern: is this to be a kernel socket?
*/
struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
struct proto *prot, int kern)
{
struct sock *sk;
sk = sk_prot_alloc(prot, priority | __GFP_ZERO, family);
if (sk) {
sk->sk_family = family;
/*
* See comment in struct sock definition to understand
* why we need sk_prot_creator -acme
*/
sk->sk_prot = sk->sk_prot_creator = prot;
net: Work around lockdep limitation in sockets that use sockets Lockdep issues a circular dependency warning when AFS issues an operation through AF_RXRPC from a context in which the VFS/VM holds the mmap_sem. The theory lockdep comes up with is as follows: (1) If the pagefault handler decides it needs to read pages from AFS, it calls AFS with mmap_sem held and AFS begins an AF_RXRPC call, but creating a call requires the socket lock: mmap_sem must be taken before sk_lock-AF_RXRPC (2) afs_open_socket() opens an AF_RXRPC socket and binds it. rxrpc_bind() binds the underlying UDP socket whilst holding its socket lock. inet_bind() takes its own socket lock: sk_lock-AF_RXRPC must be taken before sk_lock-AF_INET (3) Reading from a TCP socket into a userspace buffer might cause a fault and thus cause the kernel to take the mmap_sem, but the TCP socket is locked whilst doing this: sk_lock-AF_INET must be taken before mmap_sem However, lockdep's theory is wrong in this instance because it deals only with lock classes and not individual locks. The AF_INET lock in (2) isn't really equivalent to the AF_INET lock in (3) as the former deals with a socket entirely internal to the kernel that never sees userspace. This is a limitation in the design of lockdep. Fix the general case by: (1) Double up all the locking keys used in sockets so that one set are used if the socket is created by userspace and the other set is used if the socket is created by the kernel. (2) Store the kern parameter passed to sk_alloc() in a variable in the sock struct (sk_kern_sock). This informs sock_lock_init(), sock_init_data() and sk_clone_lock() as to the lock keys to be used. Note that the child created by sk_clone_lock() inherits the parent's kern setting. (3) Add a 'kern' parameter to ->accept() that is analogous to the one passed in to ->create() that distinguishes whether kernel_accept() or sys_accept4() was the caller and can be passed to sk_alloc(). Note that a lot of accept functions merely dequeue an already allocated socket. I haven't touched these as the new socket already exists before we get the parameter. Note also that there are a couple of places where I've made the accepted socket unconditionally kernel-based: irda_accept() rds_rcp_accept_one() tcp_accept_from_sock() because they follow a sock_create_kern() and accept off of that. Whilst creating this, I noticed that lustre and ocfs don't create sockets through sock_create_kern() and thus they aren't marked as for-kernel, though they appear to be internal. I wonder if these should do that so that they use the new set of lock keys. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-09 08:09:05 +00:00
sk->sk_kern_sock = kern;
sock_lock_init(sk);
sk->sk_net_refcnt = kern ? 0 : 1;
if (likely(sk->sk_net_refcnt)) {
get_net(net);
sock_inuse_add(net, 1);
}
sock_net_set(sk, net);
refcount_set(&sk->sk_wmem_alloc, 1);
cls_cgroup: Store classid in struct sock Up until now cls_cgroup has relied on fetching the classid out of the current executing thread. This runs into trouble when a packet processing is delayed in which case it may execute out of another thread's context. Furthermore, even when a packet is not delayed we may fail to classify it if soft IRQs have been disabled, because this scenario is indistinguishable from one where a packet unrelated to the current thread is processed by a real soft IRQ. In fact, the current semantics is inherently broken, as a single skb may be constructed out of the writes of two different tasks. A different manifestation of this problem is when the TCP stack transmits in response of an incoming ACK. This is currently unclassified. As we already have a concept of packet ownership for accounting purposes in the skb->sk pointer, this is a natural place to store the classid in a persistent manner. This patch adds the cls_cgroup classid in struct sock, filling up an existing hole on 64-bit :) The value is set at socket creation time. So all sockets created via socket(2) automatically gains the ID of the thread creating it. Whenever another process touches the socket by either reading or writing to it, we will change the socket classid to that of the process if it has a valid (non-zero) classid. For sockets created on inbound connections through accept(2), we inherit the classid of the original listening socket through sk_clone, possibly preceding the actual accept(2) call. In order to minimise risks, I have not made this the authoritative classid. For now it is only used as a backup when we execute with soft IRQs disabled. Once we're completely happy with its semantics we can use it as the sole classid. Footnote: I have rearranged the error path on cls_group module creation. If we didn't do this, then there is a window where someone could create a tc rule using cls_group before the cgroup subsystem has been registered. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-05-24 07:12:34 +00:00
mem_cgroup_sk_alloc(sk);
cgroup_sk_alloc(&sk->sk_cgrp_data);
sock_update_classid(&sk->sk_cgrp_data);
sock_update_netprioidx(&sk->sk_cgrp_data);
sk_tx_queue_clear(sk);
}
[NET]: Fix module reference counts for loadable protocol modules I have been experimenting with loadable protocol modules, and ran into several issues with module reference counting. The first issue was that __module_get failed at the BUG_ON check at the top of the routine (checking that my module reference count was not zero) when I created the first socket. When sk_alloc() is called, my module reference count was still 0. When I looked at why sctp didn't have this problem, I discovered that sctp creates a control socket during module init (when the module ref count is not 0), which keeps the reference count non-zero. This section has been updated to address the point Stephen raised about checking the return value of try_module_get(). The next problem arose when my socket init routine returned an error. This resulted in my module reference count being decremented below 0. My socket ops->release routine was also being called. The issue here is that sock_release() calls the ops->release routine and decrements the ref count if sock->ops is not NULL. Since the socket probably didn't get correctly initialized, this should not be done, so we will set sock->ops to NULL because we will not call try_module_get(). While searching for another bug, I also noticed that sys_accept() has a possibility of doing a module_put() when it did not do an __module_get so I re-ordered the call to security_socket_accept(). Signed-off-by: Frank Filz <ffilzlnx@us.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-09-27 22:23:38 +00:00
return sk;
}
EXPORT_SYMBOL(sk_alloc);
/* Sockets having SOCK_RCU_FREE will call this function after one RCU
* grace period. This is the case for UDP sockets and TCP listeners.
*/
static void __sk_destruct(struct rcu_head *head)
{
struct sock *sk = container_of(head, struct sock, sk_rcu);
struct sk_filter *filter;
if (sk->sk_destruct)
sk->sk_destruct(sk);
filter = rcu_dereference_check(sk->sk_filter,
refcount_read(&sk->sk_wmem_alloc) == 0);
if (filter) {
sk_filter_uncharge(sk, filter);
RCU_INIT_POINTER(sk->sk_filter, NULL);
}
sock_disable_timestamp(sk, SK_FLAGS_TIMESTAMP);
bpf: Introduce bpf sk local storage After allowing a bpf prog to - directly read the skb->sk ptr - get the fullsock bpf_sock by "bpf_sk_fullsock()" - get the bpf_tcp_sock by "bpf_tcp_sock()" - get the listener sock by "bpf_get_listener_sock()" - avoid duplicating the fields of "(bpf_)sock" and "(bpf_)tcp_sock" into different bpf running context. this patch is another effort to make bpf's network programming more intuitive to do (together with memory and performance benefit). When bpf prog needs to store data for a sk, the current practice is to define a map with the usual 4-tuples (src/dst ip/port) as the key. If multiple bpf progs require to store different sk data, multiple maps have to be defined. Hence, wasting memory to store the duplicated keys (i.e. 4 tuples here) in each of the bpf map. [ The smallest key could be the sk pointer itself which requires some enhancement in the verifier and it is a separate topic. ] Also, the bpf prog needs to clean up the elem when sk is freed. Otherwise, the bpf map will become full and un-usable quickly. The sk-free tracking currently could be done during sk state transition (e.g. BPF_SOCK_OPS_STATE_CB). The size of the map needs to be predefined which then usually ended-up with an over-provisioned map in production. Even the map was re-sizable, while the sk naturally come and go away already, this potential re-size operation is arguably redundant if the data can be directly connected to the sk itself instead of proxy-ing through a bpf map. This patch introduces sk->sk_bpf_storage to provide local storage space at sk for bpf prog to use. The space will be allocated when the first bpf prog has created data for this particular sk. The design optimizes the bpf prog's lookup (and then optionally followed by an inline update). bpf_spin_lock should be used if the inline update needs to be protected. BPF_MAP_TYPE_SK_STORAGE: ----------------------- To define a bpf "sk-local-storage", a BPF_MAP_TYPE_SK_STORAGE map (new in this patch) needs to be created. Multiple BPF_MAP_TYPE_SK_STORAGE maps can be created to fit different bpf progs' needs. The map enforces BTF to allow printing the sk-local-storage during a system-wise sk dump (e.g. "ss -ta") in the future. The purpose of a BPF_MAP_TYPE_SK_STORAGE map is not for lookup/update/delete a "sk-local-storage" data from a particular sk. Think of the map as a meta-data (or "type") of a "sk-local-storage". This particular "type" of "sk-local-storage" data can then be stored in any sk. The main purposes of this map are mostly: 1. Define the size of a "sk-local-storage" type. 2. Provide a similar syscall userspace API as the map (e.g. lookup/update, map-id, map-btf...etc.) 3. Keep track of all sk's storages of this "type" and clean them up when the map is freed. sk->sk_bpf_storage: ------------------ The main lookup/update/delete is done on sk->sk_bpf_storage (which is a "struct bpf_sk_storage"). When doing a lookup, the "map" pointer is now used as the "key" to search on the sk_storage->list. The "map" pointer is actually serving as the "type" of the "sk-local-storage" that is being requested. To allow very fast lookup, it should be as fast as looking up an array at a stable-offset. At the same time, it is not ideal to set a hard limit on the number of sk-local-storage "type" that the system can have. Hence, this patch takes a cache approach. The last search result from sk_storage->list is cached in sk_storage->cache[] which is a stable sized array. Each "sk-local-storage" type has a stable offset to the cache[] array. In the future, a map's flag could be introduced to do cache opt-out/enforcement if it became necessary. The cache size is 16 (i.e. 16 types of "sk-local-storage"). Programs can share map. On the program side, having a few bpf_progs running in the networking hotpath is already a lot. The bpf_prog should have already consolidated the existing sock-key-ed map usage to minimize the map lookup penalty. 16 has enough runway to grow. All sk-local-storage data will be removed from sk->sk_bpf_storage during sk destruction. bpf_sk_storage_get() and bpf_sk_storage_delete(): ------------------------------------------------ Instead of using bpf_map_(lookup|update|delete)_elem(), the bpf prog needs to use the new helper bpf_sk_storage_get() and bpf_sk_storage_delete(). The verifier can then enforce the ARG_PTR_TO_SOCKET argument. The bpf_sk_storage_get() also allows to "create" new elem if one does not exist in the sk. It is done by the new BPF_SK_STORAGE_GET_F_CREATE flag. An optional value can also be provided as the initial value during BPF_SK_STORAGE_GET_F_CREATE. The BPF_MAP_TYPE_SK_STORAGE also supports bpf_spin_lock. Together, it has eliminated the potential use cases for an equivalent bpf_map_update_elem() API (for bpf_prog) in this patch. Misc notes: ---------- 1. map_get_next_key is not supported. From the userspace syscall perspective, the map has the socket fd as the key while the map can be shared by pinned-file or map-id. Since btf is enforced, the existing "ss" could be enhanced to pretty print the local-storage. Supporting a kernel defined btf with 4 tuples as the return key could be explored later also. 2. The sk->sk_lock cannot be acquired. Atomic operations is used instead. e.g. cmpxchg is done on the sk->sk_bpf_storage ptr. Please refer to the source code comments for the details in synchronization cases and considerations. 3. The mem is charged to the sk->sk_omem_alloc as the sk filter does. Benchmark: --------- Here is the benchmark data collected by turning on the "kernel.bpf_stats_enabled" sysctl. Two bpf progs are tested: One bpf prog with the usual bpf hashmap (max_entries = 8192) with the sk ptr as the key. (verifier is modified to support sk ptr as the key That should have shortened the key lookup time.) Another bpf prog is with the new BPF_MAP_TYPE_SK_STORAGE. Both are storing a "u32 cnt", do a lookup on "egress_skb/cgroup" for each egress skb and then bump the cnt. netperf is used to drive data with 4096 connected UDP sockets. BPF_MAP_TYPE_HASH with a modifier verifier (152ns per bpf run) 27: cgroup_skb name egress_sk_map tag 74f56e832918070b run_time_ns 58280107540 run_cnt 381347633 loaded_at 2019-04-15T13:46:39-0700 uid 0 xlated 344B jited 258B memlock 4096B map_ids 16 btf_id 5 BPF_MAP_TYPE_SK_STORAGE in this patch (66ns per bpf run) 30: cgroup_skb name egress_sk_stora tag d4aa70984cc7bbf6 run_time_ns 25617093319 run_cnt 390989739 loaded_at 2019-04-15T13:47:54-0700 uid 0 xlated 168B jited 156B memlock 4096B map_ids 17 btf_id 6 Here is a high-level picture on how are the objects organized: sk ┌──────┐ │ │ │ │ │ │ │*sk_bpf_storage─────▶ bpf_sk_storage └──────┘ ┌───────┐ ┌───────────┤ list │ │ │ │ │ │ │ │ │ │ │ └───────┘ │ │ elem │ ┌────────┐ ├─▶│ snode │ │ ├────────┤ │ │ data │ bpf_map │ ├────────┤ ┌─────────┐ │ │map_node│◀─┬─────┤ list │ │ └────────┘ │ │ │ │ │ │ │ │ elem │ │ │ │ ┌────────┐ │ └─────────┘ └─▶│ snode │ │ ├────────┤ │ bpf_map │ data │ │ ┌─────────┐ ├────────┤ │ │ list ├───────▶│map_node│ │ │ │ └────────┘ │ │ │ │ │ │ elem │ └─────────┘ ┌────────┐ │ ┌─▶│ snode │ │ │ ├────────┤ │ │ │ data │ │ │ ├────────┤ │ │ │map_node│◀─┘ │ └────────┘ │ │ │ ┌───────┐ sk └──────────│ list │ ┌──────┐ │ │ │ │ │ │ │ │ │ │ │ │ └───────┘ │*sk_bpf_storage───────▶bpf_sk_storage └──────┘ Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-04-26 23:39:39 +00:00
#ifdef CONFIG_BPF_SYSCALL
bpf_sk_storage_free(sk);
#endif
if (atomic_read(&sk->sk_omem_alloc))
pr_debug("%s: optmem leakage (%d bytes) detected\n",
__func__, atomic_read(&sk->sk_omem_alloc));
if (sk->sk_frag.page) {
put_page(sk->sk_frag.page);
sk->sk_frag.page = NULL;
}
if (sk->sk_peer_cred)
put_cred(sk->sk_peer_cred);
put_pid(sk->sk_peer_pid);
if (likely(sk->sk_net_refcnt))
put_net(sock_net(sk));
sk_prot_free(sk->sk_prot_creator, sk);
}
net: No more expensive sock_hold()/sock_put() on each tx One of the problem with sock memory accounting is it uses a pair of sock_hold()/sock_put() for each transmitted packet. This slows down bidirectional flows because the receive path also needs to take a refcount on socket and might use a different cpu than transmit path or transmit completion path. So these two atomic operations also trigger cache line bounces. We can see this in tx or tx/rx workloads (media gateways for example), where sock_wfree() can be in top five functions in profiles. We use this sock_hold()/sock_put() so that sock freeing is delayed until all tx packets are completed. As we also update sk_wmem_alloc, we could offset sk_wmem_alloc by one unit at init time, until sk_free() is called. Once sk_free() is called, we atomic_dec_and_test(sk_wmem_alloc) to decrement initial offset and atomicaly check if any packets are in flight. skb_set_owner_w() doesnt call sock_hold() anymore sock_wfree() doesnt call sock_put() anymore, but check if sk_wmem_alloc reached 0 to perform the final freeing. Drawback is that a skb->truesize error could lead to unfreeable sockets, or even worse, prematurely calling __sk_free() on a live socket. Nice speedups on SMP. tbench for example, going from 2691 MB/s to 2711 MB/s on my 8 cpu dev machine, even if tbench was not really hitting sk_refcnt contention point. 5 % speedup on a UDP transmit workload (depends on number of flows), lowering TX completion cpu usage. Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-06-11 09:55:43 +00:00
void sk_destruct(struct sock *sk)
{
bool use_call_rcu = sock_flag(sk, SOCK_RCU_FREE);
if (rcu_access_pointer(sk->sk_reuseport_cb)) {
reuseport_detach_sock(sk);
use_call_rcu = true;
}
if (use_call_rcu)
call_rcu(&sk->sk_rcu, __sk_destruct);
else
__sk_destruct(&sk->sk_rcu);
}
static void __sk_free(struct sock *sk)
{
if (likely(sk->sk_net_refcnt))
sock_inuse_add(sock_net(sk), -1);
sock_diag: fix use-after-free read in __sk_free We must not call sock_diag_has_destroy_listeners(sk) on a socket that has no reference on net structure. BUG: KASAN: use-after-free in sock_diag_has_destroy_listeners include/linux/sock_diag.h:75 [inline] BUG: KASAN: use-after-free in __sk_free+0x329/0x340 net/core/sock.c:1609 Read of size 8 at addr ffff88018a02e3a0 by task swapper/1/0 CPU: 1 PID: 0 Comm: swapper/1 Not tainted 4.17.0-rc5+ #54 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: <IRQ> __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x1b9/0x294 lib/dump_stack.c:113 print_address_description+0x6c/0x20b mm/kasan/report.c:256 kasan_report_error mm/kasan/report.c:354 [inline] kasan_report.cold.7+0x242/0x2fe mm/kasan/report.c:412 __asan_report_load8_noabort+0x14/0x20 mm/kasan/report.c:433 sock_diag_has_destroy_listeners include/linux/sock_diag.h:75 [inline] __sk_free+0x329/0x340 net/core/sock.c:1609 sk_free+0x42/0x50 net/core/sock.c:1623 sock_put include/net/sock.h:1664 [inline] reqsk_free include/net/request_sock.h:116 [inline] reqsk_put include/net/request_sock.h:124 [inline] inet_csk_reqsk_queue_drop_and_put net/ipv4/inet_connection_sock.c:672 [inline] reqsk_timer_handler+0xe27/0x10e0 net/ipv4/inet_connection_sock.c:739 call_timer_fn+0x230/0x940 kernel/time/timer.c:1326 expire_timers kernel/time/timer.c:1363 [inline] __run_timers+0x79e/0xc50 kernel/time/timer.c:1666 run_timer_softirq+0x4c/0x70 kernel/time/timer.c:1692 __do_softirq+0x2e0/0xaf5 kernel/softirq.c:285 invoke_softirq kernel/softirq.c:365 [inline] irq_exit+0x1d1/0x200 kernel/softirq.c:405 exiting_irq arch/x86/include/asm/apic.h:525 [inline] smp_apic_timer_interrupt+0x17e/0x710 arch/x86/kernel/apic/apic.c:1052 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:863 </IRQ> RIP: 0010:native_safe_halt+0x6/0x10 arch/x86/include/asm/irqflags.h:54 RSP: 0018:ffff8801d9ae7c38 EFLAGS: 00000282 ORIG_RAX: ffffffffffffff13 RAX: dffffc0000000000 RBX: 1ffff1003b35cf8a RCX: 0000000000000000 RDX: 1ffffffff11a30d0 RSI: 0000000000000001 RDI: ffffffff88d18680 RBP: ffff8801d9ae7c38 R08: ffffed003b5e46c3 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000001 R13: ffff8801d9ae7cf0 R14: ffffffff897bef20 R15: 0000000000000000 arch_safe_halt arch/x86/include/asm/paravirt.h:94 [inline] default_idle+0xc2/0x440 arch/x86/kernel/process.c:354 arch_cpu_idle+0x10/0x20 arch/x86/kernel/process.c:345 default_idle_call+0x6d/0x90 kernel/sched/idle.c:93 cpuidle_idle_call kernel/sched/idle.c:153 [inline] do_idle+0x395/0x560 kernel/sched/idle.c:262 cpu_startup_entry+0x104/0x120 kernel/sched/idle.c:368 start_secondary+0x426/0x5b0 arch/x86/kernel/smpboot.c:269 secondary_startup_64+0xa5/0xb0 arch/x86/kernel/head_64.S:242 Allocated by task 4557: save_stack+0x43/0xd0 mm/kasan/kasan.c:448 set_track mm/kasan/kasan.c:460 [inline] kasan_kmalloc+0xc4/0xe0 mm/kasan/kasan.c:553 kasan_slab_alloc+0x12/0x20 mm/kasan/kasan.c:490 kmem_cache_alloc+0x12e/0x760 mm/slab.c:3554 kmem_cache_zalloc include/linux/slab.h:691 [inline] net_alloc net/core/net_namespace.c:383 [inline] copy_net_ns+0x159/0x4c0 net/core/net_namespace.c:423 create_new_namespaces+0x69d/0x8f0 kernel/nsproxy.c:107 unshare_nsproxy_namespaces+0xc3/0x1f0 kernel/nsproxy.c:206 ksys_unshare+0x708/0xf90 kernel/fork.c:2408 __do_sys_unshare kernel/fork.c:2476 [inline] __se_sys_unshare kernel/fork.c:2474 [inline] __x64_sys_unshare+0x31/0x40 kernel/fork.c:2474 do_syscall_64+0x1b1/0x800 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x49/0xbe Freed by task 69: save_stack+0x43/0xd0 mm/kasan/kasan.c:448 set_track mm/kasan/kasan.c:460 [inline] __kasan_slab_free+0x11a/0x170 mm/kasan/kasan.c:521 kasan_slab_free+0xe/0x10 mm/kasan/kasan.c:528 __cache_free mm/slab.c:3498 [inline] kmem_cache_free+0x86/0x2d0 mm/slab.c:3756 net_free net/core/net_namespace.c:399 [inline] net_drop_ns.part.14+0x11a/0x130 net/core/net_namespace.c:406 net_drop_ns net/core/net_namespace.c:405 [inline] cleanup_net+0x6a1/0xb20 net/core/net_namespace.c:541 process_one_work+0xc1e/0x1b50 kernel/workqueue.c:2145 worker_thread+0x1cc/0x1440 kernel/workqueue.c:2279 kthread+0x345/0x410 kernel/kthread.c:240 ret_from_fork+0x3a/0x50 arch/x86/entry/entry_64.S:412 The buggy address belongs to the object at ffff88018a02c140 which belongs to the cache net_namespace of size 8832 The buggy address is located 8800 bytes inside of 8832-byte region [ffff88018a02c140, ffff88018a02e3c0) The buggy address belongs to the page: page:ffffea0006280b00 count:1 mapcount:0 mapping:ffff88018a02c140 index:0x0 compound_mapcount: 0 flags: 0x2fffc0000008100(slab|head) raw: 02fffc0000008100 ffff88018a02c140 0000000000000000 0000000100000001 raw: ffffea00062a1320 ffffea0006268020 ffff8801d9bdde40 0000000000000000 page dumped because: kasan: bad access detected Fixes: b922622ec6ef ("sock_diag: don't broadcast kernel sockets") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Craig Gallek <kraig@google.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-18 11:47:55 +00:00
if (unlikely(sk->sk_net_refcnt && sock_diag_has_destroy_listeners(sk)))
sock_diag_broadcast_destroy(sk);
else
sk_destruct(sk);
}
net: No more expensive sock_hold()/sock_put() on each tx One of the problem with sock memory accounting is it uses a pair of sock_hold()/sock_put() for each transmitted packet. This slows down bidirectional flows because the receive path also needs to take a refcount on socket and might use a different cpu than transmit path or transmit completion path. So these two atomic operations also trigger cache line bounces. We can see this in tx or tx/rx workloads (media gateways for example), where sock_wfree() can be in top five functions in profiles. We use this sock_hold()/sock_put() so that sock freeing is delayed until all tx packets are completed. As we also update sk_wmem_alloc, we could offset sk_wmem_alloc by one unit at init time, until sk_free() is called. Once sk_free() is called, we atomic_dec_and_test(sk_wmem_alloc) to decrement initial offset and atomicaly check if any packets are in flight. skb_set_owner_w() doesnt call sock_hold() anymore sock_wfree() doesnt call sock_put() anymore, but check if sk_wmem_alloc reached 0 to perform the final freeing. Drawback is that a skb->truesize error could lead to unfreeable sockets, or even worse, prematurely calling __sk_free() on a live socket. Nice speedups on SMP. tbench for example, going from 2691 MB/s to 2711 MB/s on my 8 cpu dev machine, even if tbench was not really hitting sk_refcnt contention point. 5 % speedup on a UDP transmit workload (depends on number of flows), lowering TX completion cpu usage. Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-06-11 09:55:43 +00:00
void sk_free(struct sock *sk)
{
/*
* We subtract one from sk_wmem_alloc and can know if
net: No more expensive sock_hold()/sock_put() on each tx One of the problem with sock memory accounting is it uses a pair of sock_hold()/sock_put() for each transmitted packet. This slows down bidirectional flows because the receive path also needs to take a refcount on socket and might use a different cpu than transmit path or transmit completion path. So these two atomic operations also trigger cache line bounces. We can see this in tx or tx/rx workloads (media gateways for example), where sock_wfree() can be in top five functions in profiles. We use this sock_hold()/sock_put() so that sock freeing is delayed until all tx packets are completed. As we also update sk_wmem_alloc, we could offset sk_wmem_alloc by one unit at init time, until sk_free() is called. Once sk_free() is called, we atomic_dec_and_test(sk_wmem_alloc) to decrement initial offset and atomicaly check if any packets are in flight. skb_set_owner_w() doesnt call sock_hold() anymore sock_wfree() doesnt call sock_put() anymore, but check if sk_wmem_alloc reached 0 to perform the final freeing. Drawback is that a skb->truesize error could lead to unfreeable sockets, or even worse, prematurely calling __sk_free() on a live socket. Nice speedups on SMP. tbench for example, going from 2691 MB/s to 2711 MB/s on my 8 cpu dev machine, even if tbench was not really hitting sk_refcnt contention point. 5 % speedup on a UDP transmit workload (depends on number of flows), lowering TX completion cpu usage. Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-06-11 09:55:43 +00:00
* some packets are still in some tx queue.
* If not null, sock_wfree() will call __sk_free(sk) later
*/
if (refcount_dec_and_test(&sk->sk_wmem_alloc))
net: No more expensive sock_hold()/sock_put() on each tx One of the problem with sock memory accounting is it uses a pair of sock_hold()/sock_put() for each transmitted packet. This slows down bidirectional flows because the receive path also needs to take a refcount on socket and might use a different cpu than transmit path or transmit completion path. So these two atomic operations also trigger cache line bounces. We can see this in tx or tx/rx workloads (media gateways for example), where sock_wfree() can be in top five functions in profiles. We use this sock_hold()/sock_put() so that sock freeing is delayed until all tx packets are completed. As we also update sk_wmem_alloc, we could offset sk_wmem_alloc by one unit at init time, until sk_free() is called. Once sk_free() is called, we atomic_dec_and_test(sk_wmem_alloc) to decrement initial offset and atomicaly check if any packets are in flight. skb_set_owner_w() doesnt call sock_hold() anymore sock_wfree() doesnt call sock_put() anymore, but check if sk_wmem_alloc reached 0 to perform the final freeing. Drawback is that a skb->truesize error could lead to unfreeable sockets, or even worse, prematurely calling __sk_free() on a live socket. Nice speedups on SMP. tbench for example, going from 2691 MB/s to 2711 MB/s on my 8 cpu dev machine, even if tbench was not really hitting sk_refcnt contention point. 5 % speedup on a UDP transmit workload (depends on number of flows), lowering TX completion cpu usage. Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-06-11 09:55:43 +00:00
__sk_free(sk);
}
EXPORT_SYMBOL(sk_free);
static void sk_init_common(struct sock *sk)
{
skb_queue_head_init(&sk->sk_receive_queue);
skb_queue_head_init(&sk->sk_write_queue);
skb_queue_head_init(&sk->sk_error_queue);
rwlock_init(&sk->sk_callback_lock);
lockdep_set_class_and_name(&sk->sk_receive_queue.lock,
af_rlock_keys + sk->sk_family,
af_family_rlock_key_strings[sk->sk_family]);
lockdep_set_class_and_name(&sk->sk_write_queue.lock,
af_wlock_keys + sk->sk_family,
af_family_wlock_key_strings[sk->sk_family]);
lockdep_set_class_and_name(&sk->sk_error_queue.lock,
af_elock_keys + sk->sk_family,
af_family_elock_key_strings[sk->sk_family]);
lockdep_set_class_and_name(&sk->sk_callback_lock,
af_callback_keys + sk->sk_family,
af_family_clock_key_strings[sk->sk_family]);
}
/**
* sk_clone_lock - clone a socket, and lock its clone
* @sk: the socket to clone
* @priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc)
*
* Caller must unlock socket even in error path (bh_unlock_sock(newsk))
*/
struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
{
struct proto *prot = READ_ONCE(sk->sk_prot);
struct sk_filter *filter;
bool is_charged = true;
struct sock *newsk;
newsk = sk_prot_alloc(prot, priority, sk->sk_family);
if (!newsk)
goto out;
sock_copy(newsk, sk);
net: Set sk_prot_creator when cloning sockets to the right proto sk->sk_prot and sk->sk_prot_creator can differ when the app uses IPV6_ADDRFORM (transforming an IPv6-socket to an IPv4-one). Which is why sk_prot_creator is there to make sure that sk_prot_free() does the kmem_cache_free() on the right kmem_cache slab. Now, if such a socket gets transformed back to a listening socket (using connect() with AF_UNSPEC) we will allocate an IPv4 tcp_sock through sk_clone_lock() when a new connection comes in. But sk_prot_creator will still point to the IPv6 kmem_cache (as everything got copied in sk_clone_lock()). When freeing, we will thus put this memory back into the IPv6 kmem_cache although it was allocated in the IPv4 cache. I have seen memory corruption happening because of this. With slub-debugging and MEMCG_KMEM enabled this gives the warning "cache_from_obj: Wrong slab cache. TCPv6 but object is from TCP" A C-program to trigger this: void main(void) { int fd = socket(AF_INET6, SOCK_STREAM, IPPROTO_TCP); int new_fd, newest_fd, client_fd; struct sockaddr_in6 bind_addr; struct sockaddr_in bind_addr4, client_addr1, client_addr2; struct sockaddr unsp; int val; memset(&bind_addr, 0, sizeof(bind_addr)); bind_addr.sin6_family = AF_INET6; bind_addr.sin6_port = ntohs(42424); memset(&client_addr1, 0, sizeof(client_addr1)); client_addr1.sin_family = AF_INET; client_addr1.sin_port = ntohs(42424); client_addr1.sin_addr.s_addr = inet_addr("127.0.0.1"); memset(&client_addr2, 0, sizeof(client_addr2)); client_addr2.sin_family = AF_INET; client_addr2.sin_port = ntohs(42421); client_addr2.sin_addr.s_addr = inet_addr("127.0.0.1"); memset(&unsp, 0, sizeof(unsp)); unsp.sa_family = AF_UNSPEC; bind(fd, (struct sockaddr *)&bind_addr, sizeof(bind_addr)); listen(fd, 5); client_fd = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP); connect(client_fd, (struct sockaddr *)&client_addr1, sizeof(client_addr1)); new_fd = accept(fd, NULL, NULL); close(fd); val = AF_INET; setsockopt(new_fd, SOL_IPV6, IPV6_ADDRFORM, &val, sizeof(val)); connect(new_fd, &unsp, sizeof(unsp)); memset(&bind_addr4, 0, sizeof(bind_addr4)); bind_addr4.sin_family = AF_INET; bind_addr4.sin_port = ntohs(42421); bind(new_fd, (struct sockaddr *)&bind_addr4, sizeof(bind_addr4)); listen(new_fd, 5); client_fd = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP); connect(client_fd, (struct sockaddr *)&client_addr2, sizeof(client_addr2)); newest_fd = accept(new_fd, NULL, NULL); close(new_fd); close(client_fd); close(new_fd); } As far as I can see, this bug has been there since the beginning of the git-days. Signed-off-by: Christoph Paasch <cpaasch@apple.com> Reviewed-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-27 00:38:50 +00:00
newsk->sk_prot_creator = prot;
/* SANITY */
if (likely(newsk->sk_net_refcnt))
get_net(sock_net(newsk));
sk_node_init(&newsk->sk_node);
sock_lock_init(newsk);
bh_lock_sock(newsk);
newsk->sk_backlog.head = newsk->sk_backlog.tail = NULL;
newsk->sk_backlog.len = 0;
atomic_set(&newsk->sk_rmem_alloc, 0);
/* sk_wmem_alloc set to one (see sk_free() and sock_wfree()) */
refcount_set(&newsk->sk_wmem_alloc, 1);
atomic_set(&newsk->sk_omem_alloc, 0);
sk_init_common(newsk);
newsk->sk_dst_cache = NULL;
newsk->sk_dst_pending_confirm = 0;
newsk->sk_wmem_queued = 0;
newsk->sk_forward_alloc = 0;
atomic_set(&newsk->sk_drops, 0);
newsk->sk_send_head = NULL;
newsk->sk_userlocks = sk->sk_userlocks & ~SOCK_BINDPORT_LOCK;
atomic_set(&newsk->sk_zckey, 0);
sock_reset_flag(newsk, SOCK_DONE);
/* sk->sk_memcg will be populated at accept() time */
newsk->sk_memcg = NULL;
cgroup_sk_clone(&newsk->sk_cgrp_data);
rcu_read_lock();
filter = rcu_dereference(sk->sk_filter);
if (filter != NULL)
/* though it's an empty new sock, the charging may fail
* if sysctl_optmem_max was changed between creation of
* original socket and cloning
*/
is_charged = sk_filter_charge(newsk, filter);
RCU_INIT_POINTER(newsk->sk_filter, filter);
rcu_read_unlock();
if (unlikely(!is_charged || xfrm_sk_clone_policy(newsk, sk))) {
/* We need to make sure that we don't uncharge the new
* socket if we couldn't charge it in the first place
* as otherwise we uncharge the parent's filter.
net, sk_msg: Clear sk_user_data pointer on clone if tagged sk_user_data can hold a pointer to an object that is not intended to be shared between the parent socket and the child that gets a pointer copy on clone. This is the case when sk_user_data points at reference-counted object, like struct sk_psock. One way to resolve it is to tag the pointer with a no-copy flag by repurposing its lowest bit. Based on the bit-flag value we clear the child sk_user_data pointer after cloning the parent socket. The no-copy flag is stored in the pointer itself as opposed to externally, say in socket flags, to guarantee that the pointer and the flag are copied from parent to child socket in an atomic fashion. Parent socket state is subject to change while copying, we don't hold any locks at that time. This approach relies on an assumption that sk_user_data holds a pointer to an object aligned at least 2 bytes. A manual audit of existing users of rcu_dereference_sk_user_data helper confirms our assumption. Also, an RCU-protected sk_user_data is not likely to hold a pointer to a char value or a pathological case of "struct { char c; }". To be safe, warn when the flag-bit is set when setting sk_user_data to catch any future misuses. It is worth considering why clearing sk_user_data unconditionally is not an option. There exist users, DRBD, NVMe, and Xen drivers being among them, that rely on the pointer being copied when cloning the listening socket. Potentially we could distinguish these users by checking if the listening socket has been created in kernel-space via sock_create_kern, and hence has sk_kern_sock flag set. However, this is not the case for NVMe and Xen drivers, which create sockets without marking them as belonging to the kernel. Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Link: https://lore.kernel.org/bpf/20200218171023.844439-3-jakub@cloudflare.com
2020-02-18 17:10:14 +00:00
*/
if (!is_charged)
RCU_INIT_POINTER(newsk->sk_filter, NULL);
sk_free_unlock_clone(newsk);
newsk = NULL;
goto out;
}
RCU_INIT_POINTER(newsk->sk_reuseport_cb, NULL);
net, sk_msg: Clear sk_user_data pointer on clone if tagged sk_user_data can hold a pointer to an object that is not intended to be shared between the parent socket and the child that gets a pointer copy on clone. This is the case when sk_user_data points at reference-counted object, like struct sk_psock. One way to resolve it is to tag the pointer with a no-copy flag by repurposing its lowest bit. Based on the bit-flag value we clear the child sk_user_data pointer after cloning the parent socket. The no-copy flag is stored in the pointer itself as opposed to externally, say in socket flags, to guarantee that the pointer and the flag are copied from parent to child socket in an atomic fashion. Parent socket state is subject to change while copying, we don't hold any locks at that time. This approach relies on an assumption that sk_user_data holds a pointer to an object aligned at least 2 bytes. A manual audit of existing users of rcu_dereference_sk_user_data helper confirms our assumption. Also, an RCU-protected sk_user_data is not likely to hold a pointer to a char value or a pathological case of "struct { char c; }". To be safe, warn when the flag-bit is set when setting sk_user_data to catch any future misuses. It is worth considering why clearing sk_user_data unconditionally is not an option. There exist users, DRBD, NVMe, and Xen drivers being among them, that rely on the pointer being copied when cloning the listening socket. Potentially we could distinguish these users by checking if the listening socket has been created in kernel-space via sock_create_kern, and hence has sk_kern_sock flag set. However, this is not the case for NVMe and Xen drivers, which create sockets without marking them as belonging to the kernel. Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Link: https://lore.kernel.org/bpf/20200218171023.844439-3-jakub@cloudflare.com
2020-02-18 17:10:14 +00:00
if (bpf_sk_storage_clone(sk, newsk)) {
sk_free_unlock_clone(newsk);
newsk = NULL;
goto out;
}
/* Clear sk_user_data if parent had the pointer tagged
* as not suitable for copying when cloning.
*/
if (sk_user_data_is_nocopy(newsk))
newsk->sk_user_data = NULL;
newsk->sk_err = 0;
newsk->sk_err_soft = 0;
newsk->sk_priority = 0;
newsk->sk_incoming_cpu = raw_smp_processor_id();
if (likely(newsk->sk_net_refcnt))
sock_inuse_add(sock_net(newsk), 1);
/* Before updating sk_refcnt, we must commit prior changes to memory
* (Documentation/RCU/rculist_nulls.rst for details)
*/
smp_wmb();
refcount_set(&newsk->sk_refcnt, 2);
/* Increment the counter in the same struct proto as the master
* sock (sk_refcnt_debug_inc uses newsk->sk_prot->socks, that
* is the same as sk->sk_prot->socks, as this field was copied
* with memcpy).
*
* This _changes_ the previous behaviour, where
* tcp_create_openreq_child always was incrementing the
* equivalent to tcp_prot->socks (inet_sock_nr), so this have
* to be taken into account in all callers. -acme
*/
sk_refcnt_debug_inc(newsk);
sk_set_socket(newsk, NULL);
sk_tx_queue_clear(newsk);
RCU_INIT_POINTER(newsk->sk_wq, NULL);
if (newsk->sk_prot->sockets_allocated)
sk_sockets_allocated_inc(newsk);
if (sock_needs_netstamp(sk) && newsk->sk_flags & SK_FLAGS_TIMESTAMP)
net_enable_timestamp();
out:
return newsk;
}
EXPORT_SYMBOL_GPL(sk_clone_lock);
void sk_free_unlock_clone(struct sock *sk)
{
/* It is still raw copy of parent, so invalidate
* destructor and make plain sk_free() */
sk->sk_destruct = NULL;
bh_unlock_sock(sk);
sk_free(sk);
}
EXPORT_SYMBOL_GPL(sk_free_unlock_clone);
void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
{
u32 max_segs = 1;
sk_dst_set(sk, dst);
2018-02-19 19:56:47 +00:00
sk->sk_route_caps = dst->dev->features | sk->sk_route_forced_caps;
if (sk->sk_route_caps & NETIF_F_GSO)
sk->sk_route_caps |= NETIF_F_GSO_SOFTWARE;
sk->sk_route_caps &= ~sk->sk_route_nocaps;
if (sk_can_gso(sk)) {
if (dst->header_len && !xfrm_dst_offload_ok(dst)) {
sk->sk_route_caps &= ~NETIF_F_GSO_MASK;
[NET]: Add per-connection option to set max TSO frame size Update: My mailer ate one of Jarek's feedback mails... Fixed the parameter in netif_set_gso_max_size() to be u32, not u16. Fixed the whitespace issue due to a patch import botch. Changed the types from u32 to unsigned int to be more consistent with other variables in the area. Also brought the patch up to the latest net-2.6.26 tree. Update: Made gso_max_size container 32 bits, not 16. Moved the location of gso_max_size within netdev to be less hotpath. Made more consistent names between the sock and netdev layers, and added a define for the max GSO size. Update: Respun for net-2.6.26 tree. Update: changed max_gso_frame_size and sk_gso_max_size from signed to unsigned - thanks Stephen! This patch adds the ability for device drivers to control the size of the TSO frames being sent to them, per TCP connection. By setting the netdevice's gso_max_size value, the socket layer will set the GSO frame size based on that value. This will propogate into the TCP layer, and send TSO's of that size to the hardware. This can be desirable to help tune the bursty nature of TSO on a per-adapter basis, where one may have 1 GbE and 10 GbE devices coexisting in a system, one running multiqueue and the other not, etc. This can also be desirable for devices that cannot support full 64 KB TSO's, but still want to benefit from some level of segmentation offloading. Signed-off-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-03-21 10:43:19 +00:00
} else {
sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM;
[NET]: Add per-connection option to set max TSO frame size Update: My mailer ate one of Jarek's feedback mails... Fixed the parameter in netif_set_gso_max_size() to be u32, not u16. Fixed the whitespace issue due to a patch import botch. Changed the types from u32 to unsigned int to be more consistent with other variables in the area. Also brought the patch up to the latest net-2.6.26 tree. Update: Made gso_max_size container 32 bits, not 16. Moved the location of gso_max_size within netdev to be less hotpath. Made more consistent names between the sock and netdev layers, and added a define for the max GSO size. Update: Respun for net-2.6.26 tree. Update: changed max_gso_frame_size and sk_gso_max_size from signed to unsigned - thanks Stephen! This patch adds the ability for device drivers to control the size of the TSO frames being sent to them, per TCP connection. By setting the netdevice's gso_max_size value, the socket layer will set the GSO frame size based on that value. This will propogate into the TCP layer, and send TSO's of that size to the hardware. This can be desirable to help tune the bursty nature of TSO on a per-adapter basis, where one may have 1 GbE and 10 GbE devices coexisting in a system, one running multiqueue and the other not, etc. This can also be desirable for devices that cannot support full 64 KB TSO's, but still want to benefit from some level of segmentation offloading. Signed-off-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-03-21 10:43:19 +00:00
sk->sk_gso_max_size = dst->dev->gso_max_size;
max_segs = max_t(u32, dst->dev->gso_max_segs, 1);
[NET]: Add per-connection option to set max TSO frame size Update: My mailer ate one of Jarek's feedback mails... Fixed the parameter in netif_set_gso_max_size() to be u32, not u16. Fixed the whitespace issue due to a patch import botch. Changed the types from u32 to unsigned int to be more consistent with other variables in the area. Also brought the patch up to the latest net-2.6.26 tree. Update: Made gso_max_size container 32 bits, not 16. Moved the location of gso_max_size within netdev to be less hotpath. Made more consistent names between the sock and netdev layers, and added a define for the max GSO size. Update: Respun for net-2.6.26 tree. Update: changed max_gso_frame_size and sk_gso_max_size from signed to unsigned - thanks Stephen! This patch adds the ability for device drivers to control the size of the TSO frames being sent to them, per TCP connection. By setting the netdevice's gso_max_size value, the socket layer will set the GSO frame size based on that value. This will propogate into the TCP layer, and send TSO's of that size to the hardware. This can be desirable to help tune the bursty nature of TSO on a per-adapter basis, where one may have 1 GbE and 10 GbE devices coexisting in a system, one running multiqueue and the other not, etc. This can also be desirable for devices that cannot support full 64 KB TSO's, but still want to benefit from some level of segmentation offloading. Signed-off-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-03-21 10:43:19 +00:00
}
}
sk->sk_gso_max_segs = max_segs;
}
EXPORT_SYMBOL_GPL(sk_setup_caps);
/*
* Simple resource managers for sockets.
*/
/*
* Write buffer destructor automatically called from kfree_skb.
*/
void sock_wfree(struct sk_buff *skb)
{
struct sock *sk = skb->sk;
unsigned int len = skb->truesize;
if (!sock_flag(sk, SOCK_USE_WRITE_QUEUE)) {
/*
* Keep a reference on sk_wmem_alloc, this will be released
* after sk_write_space() call
*/
WARN_ON(refcount_sub_and_test(len - 1, &sk->sk_wmem_alloc));
sk->sk_write_space(sk);
len = 1;
}
net: No more expensive sock_hold()/sock_put() on each tx One of the problem with sock memory accounting is it uses a pair of sock_hold()/sock_put() for each transmitted packet. This slows down bidirectional flows because the receive path also needs to take a refcount on socket and might use a different cpu than transmit path or transmit completion path. So these two atomic operations also trigger cache line bounces. We can see this in tx or tx/rx workloads (media gateways for example), where sock_wfree() can be in top five functions in profiles. We use this sock_hold()/sock_put() so that sock freeing is delayed until all tx packets are completed. As we also update sk_wmem_alloc, we could offset sk_wmem_alloc by one unit at init time, until sk_free() is called. Once sk_free() is called, we atomic_dec_and_test(sk_wmem_alloc) to decrement initial offset and atomicaly check if any packets are in flight. skb_set_owner_w() doesnt call sock_hold() anymore sock_wfree() doesnt call sock_put() anymore, but check if sk_wmem_alloc reached 0 to perform the final freeing. Drawback is that a skb->truesize error could lead to unfreeable sockets, or even worse, prematurely calling __sk_free() on a live socket. Nice speedups on SMP. tbench for example, going from 2691 MB/s to 2711 MB/s on my 8 cpu dev machine, even if tbench was not really hitting sk_refcnt contention point. 5 % speedup on a UDP transmit workload (depends on number of flows), lowering TX completion cpu usage. Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-06-11 09:55:43 +00:00
/*
* if sk_wmem_alloc reaches 0, we must finish what sk_free()
* could not do because of in-flight packets
net: No more expensive sock_hold()/sock_put() on each tx One of the problem with sock memory accounting is it uses a pair of sock_hold()/sock_put() for each transmitted packet. This slows down bidirectional flows because the receive path also needs to take a refcount on socket and might use a different cpu than transmit path or transmit completion path. So these two atomic operations also trigger cache line bounces. We can see this in tx or tx/rx workloads (media gateways for example), where sock_wfree() can be in top five functions in profiles. We use this sock_hold()/sock_put() so that sock freeing is delayed until all tx packets are completed. As we also update sk_wmem_alloc, we could offset sk_wmem_alloc by one unit at init time, until sk_free() is called. Once sk_free() is called, we atomic_dec_and_test(sk_wmem_alloc) to decrement initial offset and atomicaly check if any packets are in flight. skb_set_owner_w() doesnt call sock_hold() anymore sock_wfree() doesnt call sock_put() anymore, but check if sk_wmem_alloc reached 0 to perform the final freeing. Drawback is that a skb->truesize error could lead to unfreeable sockets, or even worse, prematurely calling __sk_free() on a live socket. Nice speedups on SMP. tbench for example, going from 2691 MB/s to 2711 MB/s on my 8 cpu dev machine, even if tbench was not really hitting sk_refcnt contention point. 5 % speedup on a UDP transmit workload (depends on number of flows), lowering TX completion cpu usage. Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-06-11 09:55:43 +00:00
*/
if (refcount_sub_and_test(len, &sk->sk_wmem_alloc))
net: No more expensive sock_hold()/sock_put() on each tx One of the problem with sock memory accounting is it uses a pair of sock_hold()/sock_put() for each transmitted packet. This slows down bidirectional flows because the receive path also needs to take a refcount on socket and might use a different cpu than transmit path or transmit completion path. So these two atomic operations also trigger cache line bounces. We can see this in tx or tx/rx workloads (media gateways for example), where sock_wfree() can be in top five functions in profiles. We use this sock_hold()/sock_put() so that sock freeing is delayed until all tx packets are completed. As we also update sk_wmem_alloc, we could offset sk_wmem_alloc by one unit at init time, until sk_free() is called. Once sk_free() is called, we atomic_dec_and_test(sk_wmem_alloc) to decrement initial offset and atomicaly check if any packets are in flight. skb_set_owner_w() doesnt call sock_hold() anymore sock_wfree() doesnt call sock_put() anymore, but check if sk_wmem_alloc reached 0 to perform the final freeing. Drawback is that a skb->truesize error could lead to unfreeable sockets, or even worse, prematurely calling __sk_free() on a live socket. Nice speedups on SMP. tbench for example, going from 2691 MB/s to 2711 MB/s on my 8 cpu dev machine, even if tbench was not really hitting sk_refcnt contention point. 5 % speedup on a UDP transmit workload (depends on number of flows), lowering TX completion cpu usage. Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-06-11 09:55:43 +00:00
__sk_free(sk);
}
EXPORT_SYMBOL(sock_wfree);
/* This variant of sock_wfree() is used by TCP,
* since it sets SOCK_USE_WRITE_QUEUE.
*/
void __sock_wfree(struct sk_buff *skb)
{
struct sock *sk = skb->sk;
if (refcount_sub_and_test(skb->truesize, &sk->sk_wmem_alloc))
__sk_free(sk);
}
void skb_set_owner_w(struct sk_buff *skb, struct sock *sk)
{
skb_orphan(skb);
skb->sk = sk;
#ifdef CONFIG_INET
if (unlikely(!sk_fullsock(sk))) {
skb->destructor = sock_edemux;
sock_hold(sk);
return;
}
#endif
skb->destructor = sock_wfree;
skb_set_hash_from_sk(skb, sk);
/*
* We used to take a refcount on sk, but following operation
* is enough to guarantee sk_free() wont free this sock until
* all in-flight packets are completed
*/
refcount_add(skb->truesize, &sk->sk_wmem_alloc);
}
EXPORT_SYMBOL(skb_set_owner_w);
net/tls: prevent skb_orphan() from leaking TLS plain text with offload sk_validate_xmit_skb() and drivers depend on the sk member of struct sk_buff to identify segments requiring encryption. Any operation which removes or does not preserve the original TLS socket such as skb_orphan() or skb_clone() will cause clear text leaks. Make the TCP socket underlying an offloaded TLS connection mark all skbs as decrypted, if TLS TX is in offload mode. Then in sk_validate_xmit_skb() catch skbs which have no socket (or a socket with no validation) and decrypted flag set. Note that CONFIG_SOCK_VALIDATE_XMIT, CONFIG_TLS_DEVICE and sk->sk_validate_xmit_skb are slightly interchangeable right now, they all imply TLS offload. The new checks are guarded by CONFIG_TLS_DEVICE because that's the option guarding the sk_buff->decrypted member. Second, smaller issue with orphaning is that it breaks the guarantee that packets will be delivered to device queues in-order. All TLS offload drivers depend on that scheduling property. This means skb_orphan_partial()'s trick of preserving partial socket references will cause issues in the drivers. We need a full orphan, and as a result netem delay/throttling will cause all TLS offload skbs to be dropped. Reusing the sk_buff->decrypted flag also protects from leaking clear text when incoming, decrypted skb is redirected (e.g. by TC). See commit 0608c69c9a80 ("bpf: sk_msg, sock{map|hash} redirect through ULP") for justification why the internal flag is safe. The only location which could leak the flag in is tcp_bpf_sendmsg(), which is taken care of by clearing the previously unused bit. v2: - remove superfluous decrypted mark copy (Willem); - remove the stale doc entry (Boris); - rely entirely on EOR marking to prevent coalescing (Boris); - use an internal sendpages flag instead of marking the socket (Boris). v3 (Willem): - reorganize the can_skb_orphan_partial() condition; - fix the flag leak-in through tcp_bpf_sendmsg. Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com> Acked-by: Willem de Bruijn <willemb@google.com> Reviewed-by: Boris Pismenny <borisp@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-08-08 00:03:59 +00:00
static bool can_skb_orphan_partial(const struct sk_buff *skb)
{
#ifdef CONFIG_TLS_DEVICE
/* Drivers depend on in-order delivery for crypto offload,
* partial orphan breaks out-of-order-OK logic.
*/
if (skb->decrypted)
return false;
#endif
return (skb->destructor == sock_wfree ||
(IS_ENABLED(CONFIG_INET) && skb->destructor == tcp_wfree));
}
/* This helper is used by netem, as it can hold packets in its
* delay queue. We want to allow the owner socket to send more
* packets, as if they were already TX completed by a typical driver.
* But we also want to keep skb->sk set because some packet schedulers
* rely on it (sch_fq for example).
*/
void skb_orphan_partial(struct sk_buff *skb)
{
if (skb_is_tcp_pure_ack(skb))
return;
net/tls: prevent skb_orphan() from leaking TLS plain text with offload sk_validate_xmit_skb() and drivers depend on the sk member of struct sk_buff to identify segments requiring encryption. Any operation which removes or does not preserve the original TLS socket such as skb_orphan() or skb_clone() will cause clear text leaks. Make the TCP socket underlying an offloaded TLS connection mark all skbs as decrypted, if TLS TX is in offload mode. Then in sk_validate_xmit_skb() catch skbs which have no socket (or a socket with no validation) and decrypted flag set. Note that CONFIG_SOCK_VALIDATE_XMIT, CONFIG_TLS_DEVICE and sk->sk_validate_xmit_skb are slightly interchangeable right now, they all imply TLS offload. The new checks are guarded by CONFIG_TLS_DEVICE because that's the option guarding the sk_buff->decrypted member. Second, smaller issue with orphaning is that it breaks the guarantee that packets will be delivered to device queues in-order. All TLS offload drivers depend on that scheduling property. This means skb_orphan_partial()'s trick of preserving partial socket references will cause issues in the drivers. We need a full orphan, and as a result netem delay/throttling will cause all TLS offload skbs to be dropped. Reusing the sk_buff->decrypted flag also protects from leaking clear text when incoming, decrypted skb is redirected (e.g. by TC). See commit 0608c69c9a80 ("bpf: sk_msg, sock{map|hash} redirect through ULP") for justification why the internal flag is safe. The only location which could leak the flag in is tcp_bpf_sendmsg(), which is taken care of by clearing the previously unused bit. v2: - remove superfluous decrypted mark copy (Willem); - remove the stale doc entry (Boris); - rely entirely on EOR marking to prevent coalescing (Boris); - use an internal sendpages flag instead of marking the socket (Boris). v3 (Willem): - reorganize the can_skb_orphan_partial() condition; - fix the flag leak-in through tcp_bpf_sendmsg. Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com> Acked-by: Willem de Bruijn <willemb@google.com> Reviewed-by: Boris Pismenny <borisp@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-08-08 00:03:59 +00:00
if (can_skb_orphan_partial(skb)) {
struct sock *sk = skb->sk;
if (refcount_inc_not_zero(&sk->sk_refcnt)) {
WARN_ON(refcount_sub_and_test(skb->truesize, &sk->sk_wmem_alloc));
skb->destructor = sock_efree;
}
} else {
skb_orphan(skb);
}
}
EXPORT_SYMBOL(skb_orphan_partial);
/*
* Read buffer destructor automatically called from kfree_skb.
*/
void sock_rfree(struct sk_buff *skb)
{
struct sock *sk = skb->sk;
unsigned int len = skb->truesize;
atomic_sub(len, &sk->sk_rmem_alloc);
sk_mem_uncharge(sk, len);
}
EXPORT_SYMBOL(sock_rfree);
/*
* Buffer destructor for skbs that are not used directly in read or write
* path, e.g. for error handler skbs. Automatically called from kfree_skb.
*/
void sock_efree(struct sk_buff *skb)
{
sock_put(skb->sk);
}
EXPORT_SYMBOL(sock_efree);
/* Buffer destructor for prefetch/receive path where reference count may
* not be held, e.g. for listen sockets.
*/
#ifdef CONFIG_INET
void sock_pfree(struct sk_buff *skb)
{
if (sk_is_refcounted(skb->sk))
sock_gen_put(skb->sk);
}
EXPORT_SYMBOL(sock_pfree);
#endif /* CONFIG_INET */
kuid_t sock_i_uid(struct sock *sk)
{
kuid_t uid;
net: fix a lockdep splat We have for each socket : One spinlock (sk_slock.slock) One rwlock (sk_callback_lock) Possible scenarios are : (A) (this is used in net/sunrpc/xprtsock.c) read_lock(&sk->sk_callback_lock) (without blocking BH) <BH> spin_lock(&sk->sk_slock.slock); ... read_lock(&sk->sk_callback_lock); ... (B) write_lock_bh(&sk->sk_callback_lock) stuff write_unlock_bh(&sk->sk_callback_lock) (C) spin_lock_bh(&sk->sk_slock) ... write_lock_bh(&sk->sk_callback_lock) stuff write_unlock_bh(&sk->sk_callback_lock) spin_unlock_bh(&sk->sk_slock) This (C) case conflicts with (A) : CPU1 [A] CPU2 [C] read_lock(callback_lock) <BH> spin_lock_bh(slock) <wait to spin_lock(slock)> <wait to write_lock_bh(callback_lock)> We have one problematic (C) use case in inet_csk_listen_stop() : local_bh_disable(); bh_lock_sock(child); // spin_lock_bh(&sk->sk_slock) WARN_ON(sock_owned_by_user(child)); ... sock_orphan(child); // write_lock_bh(&sk->sk_callback_lock) lockdep is not happy with this, as reported by Tetsuo Handa It seems only way to deal with this is to use read_lock_bh(callbacklock) everywhere. Thanks to Jarek for pointing a bug in my first attempt and suggesting this solution. Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Tested-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> CC: Jarek Poplawski <jarkao2@gmail.com> Tested-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-09-22 12:43:39 +00:00
read_lock_bh(&sk->sk_callback_lock);
uid = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_uid : GLOBAL_ROOT_UID;
net: fix a lockdep splat We have for each socket : One spinlock (sk_slock.slock) One rwlock (sk_callback_lock) Possible scenarios are : (A) (this is used in net/sunrpc/xprtsock.c) read_lock(&sk->sk_callback_lock) (without blocking BH) <BH> spin_lock(&sk->sk_slock.slock); ... read_lock(&sk->sk_callback_lock); ... (B) write_lock_bh(&sk->sk_callback_lock) stuff write_unlock_bh(&sk->sk_callback_lock) (C) spin_lock_bh(&sk->sk_slock) ... write_lock_bh(&sk->sk_callback_lock) stuff write_unlock_bh(&sk->sk_callback_lock) spin_unlock_bh(&sk->sk_slock) This (C) case conflicts with (A) : CPU1 [A] CPU2 [C] read_lock(callback_lock) <BH> spin_lock_bh(slock) <wait to spin_lock(slock)> <wait to write_lock_bh(callback_lock)> We have one problematic (C) use case in inet_csk_listen_stop() : local_bh_disable(); bh_lock_sock(child); // spin_lock_bh(&sk->sk_slock) WARN_ON(sock_owned_by_user(child)); ... sock_orphan(child); // write_lock_bh(&sk->sk_callback_lock) lockdep is not happy with this, as reported by Tetsuo Handa It seems only way to deal with this is to use read_lock_bh(callbacklock) everywhere. Thanks to Jarek for pointing a bug in my first attempt and suggesting this solution. Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Tested-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> CC: Jarek Poplawski <jarkao2@gmail.com> Tested-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-09-22 12:43:39 +00:00
read_unlock_bh(&sk->sk_callback_lock);
return uid;
}
EXPORT_SYMBOL(sock_i_uid);
unsigned long sock_i_ino(struct sock *sk)
{
unsigned long ino;
net: fix a lockdep splat We have for each socket : One spinlock (sk_slock.slock) One rwlock (sk_callback_lock) Possible scenarios are : (A) (this is used in net/sunrpc/xprtsock.c) read_lock(&sk->sk_callback_lock) (without blocking BH) <BH> spin_lock(&sk->sk_slock.slock); ... read_lock(&sk->sk_callback_lock); ... (B) write_lock_bh(&sk->sk_callback_lock) stuff write_unlock_bh(&sk->sk_callback_lock) (C) spin_lock_bh(&sk->sk_slock) ... write_lock_bh(&sk->sk_callback_lock) stuff write_unlock_bh(&sk->sk_callback_lock) spin_unlock_bh(&sk->sk_slock) This (C) case conflicts with (A) : CPU1 [A] CPU2 [C] read_lock(callback_lock) <BH> spin_lock_bh(slock) <wait to spin_lock(slock)> <wait to write_lock_bh(callback_lock)> We have one problematic (C) use case in inet_csk_listen_stop() : local_bh_disable(); bh_lock_sock(child); // spin_lock_bh(&sk->sk_slock) WARN_ON(sock_owned_by_user(child)); ... sock_orphan(child); // write_lock_bh(&sk->sk_callback_lock) lockdep is not happy with this, as reported by Tetsuo Handa It seems only way to deal with this is to use read_lock_bh(callbacklock) everywhere. Thanks to Jarek for pointing a bug in my first attempt and suggesting this solution. Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Tested-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> CC: Jarek Poplawski <jarkao2@gmail.com> Tested-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-09-22 12:43:39 +00:00
read_lock_bh(&sk->sk_callback_lock);
ino = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_ino : 0;
net: fix a lockdep splat We have for each socket : One spinlock (sk_slock.slock) One rwlock (sk_callback_lock) Possible scenarios are : (A) (this is used in net/sunrpc/xprtsock.c) read_lock(&sk->sk_callback_lock) (without blocking BH) <BH> spin_lock(&sk->sk_slock.slock); ... read_lock(&sk->sk_callback_lock); ... (B) write_lock_bh(&sk->sk_callback_lock) stuff write_unlock_bh(&sk->sk_callback_lock) (C) spin_lock_bh(&sk->sk_slock) ... write_lock_bh(&sk->sk_callback_lock) stuff write_unlock_bh(&sk->sk_callback_lock) spin_unlock_bh(&sk->sk_slock) This (C) case conflicts with (A) : CPU1 [A] CPU2 [C] read_lock(callback_lock) <BH> spin_lock_bh(slock) <wait to spin_lock(slock)> <wait to write_lock_bh(callback_lock)> We have one problematic (C) use case in inet_csk_listen_stop() : local_bh_disable(); bh_lock_sock(child); // spin_lock_bh(&sk->sk_slock) WARN_ON(sock_owned_by_user(child)); ... sock_orphan(child); // write_lock_bh(&sk->sk_callback_lock) lockdep is not happy with this, as reported by Tetsuo Handa It seems only way to deal with this is to use read_lock_bh(callbacklock) everywhere. Thanks to Jarek for pointing a bug in my first attempt and suggesting this solution. Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Tested-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> CC: Jarek Poplawski <jarkao2@gmail.com> Tested-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-09-22 12:43:39 +00:00
read_unlock_bh(&sk->sk_callback_lock);
return ino;
}
EXPORT_SYMBOL(sock_i_ino);
/*
* Allocate a skb from the socket's send buffer.
*/
struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force,
gfp_t priority)
{
if (force ||
refcount_read(&sk->sk_wmem_alloc) < READ_ONCE(sk->sk_sndbuf)) {
struct sk_buff *skb = alloc_skb(size, priority);
if (skb) {
skb_set_owner_w(skb, sk);
return skb;
}
}
return NULL;
}
EXPORT_SYMBOL(sock_wmalloc);
static void sock_ofree(struct sk_buff *skb)
{
struct sock *sk = skb->sk;
atomic_sub(skb->truesize, &sk->sk_omem_alloc);
}
struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size,
gfp_t priority)
{
struct sk_buff *skb;
/* small safe race: SKB_TRUESIZE may differ from final skb->truesize */
if (atomic_read(&sk->sk_omem_alloc) + SKB_TRUESIZE(size) >
sysctl_optmem_max)
return NULL;
skb = alloc_skb(size, priority);
if (!skb)
return NULL;
atomic_add(skb->truesize, &sk->sk_omem_alloc);
skb->sk = sk;
skb->destructor = sock_ofree;
return skb;
}
/*
* Allocate a memory block from the socket's option memory buffer.
*/
void *sock_kmalloc(struct sock *sk, int size, gfp_t priority)
{
if ((unsigned int)size <= sysctl_optmem_max &&
atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) {
void *mem;
/* First do the add, to avoid the race if kmalloc
* might sleep.
*/
atomic_add(size, &sk->sk_omem_alloc);
mem = kmalloc(size, priority);
if (mem)
return mem;
atomic_sub(size, &sk->sk_omem_alloc);
}
return NULL;
}
EXPORT_SYMBOL(sock_kmalloc);
/* Free an option memory block. Note, we actually want the inline
* here as this allows gcc to detect the nullify and fold away the
* condition entirely.
*/
static inline void __sock_kfree_s(struct sock *sk, void *mem, int size,
const bool nullify)
{
if (WARN_ON_ONCE(!mem))
return;
if (nullify)
mm, treewide: rename kzfree() to kfree_sensitive() As said by Linus: A symmetric naming is only helpful if it implies symmetries in use. Otherwise it's actively misleading. In "kzalloc()", the z is meaningful and an important part of what the caller wants. In "kzfree()", the z is actively detrimental, because maybe in the future we really _might_ want to use that "memfill(0xdeadbeef)" or something. The "zero" part of the interface isn't even _relevant_. The main reason that kzfree() exists is to clear sensitive information that should not be leaked to other future users of the same memory objects. Rename kzfree() to kfree_sensitive() to follow the example of the recently added kvfree_sensitive() and make the intention of the API more explicit. In addition, memzero_explicit() is used to clear the memory to make sure that it won't get optimized away by the compiler. The renaming is done by using the command sequence: git grep -w --name-only kzfree |\ xargs sed -i 's/kzfree/kfree_sensitive/' followed by some editing of the kfree_sensitive() kerneldoc and adding a kzfree backward compatibility macro in slab.h. [akpm@linux-foundation.org: fs/crypto/inline_crypt.c needs linux/slab.h] [akpm@linux-foundation.org: fix fs/crypto/inline_crypt.c some more] Suggested-by: Joe Perches <joe@perches.com> Signed-off-by: Waiman Long <longman@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Acked-by: David Howells <dhowells@redhat.com> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com> Cc: James Morris <jmorris@namei.org> Cc: "Serge E. Hallyn" <serge@hallyn.com> Cc: Joe Perches <joe@perches.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: David Rientjes <rientjes@google.com> Cc: Dan Carpenter <dan.carpenter@oracle.com> Cc: "Jason A . Donenfeld" <Jason@zx2c4.com> Link: http://lkml.kernel.org/r/20200616154311.12314-3-longman@redhat.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-07 06:18:13 +00:00
kfree_sensitive(mem);
else
kfree(mem);
atomic_sub(size, &sk->sk_omem_alloc);
}
void sock_kfree_s(struct sock *sk, void *mem, int size)
{
__sock_kfree_s(sk, mem, size, false);
}
EXPORT_SYMBOL(sock_kfree_s);
void sock_kzfree_s(struct sock *sk, void *mem, int size)
{
__sock_kfree_s(sk, mem, size, true);
}
EXPORT_SYMBOL(sock_kzfree_s);
/* It is almost wait_for_tcp_memory minus release_sock/lock_sock.
I think, these locks should be removed for datagram sockets.
*/
static long sock_wait_for_wmem(struct sock *sk, long timeo)
{
DEFINE_WAIT(wait);
sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
for (;;) {
if (!timeo)
break;
if (signal_pending(current))
break;
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
if (refcount_read(&sk->sk_wmem_alloc) < READ_ONCE(sk->sk_sndbuf))
break;
if (sk->sk_shutdown & SEND_SHUTDOWN)
break;
if (sk->sk_err)
break;
timeo = schedule_timeout(timeo);
}
finish_wait(sk_sleep(sk), &wait);
return timeo;
}
/*
* Generic send/receive buffer handlers
*/
struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
unsigned long data_len, int noblock,
int *errcode, int max_page_order)
{
struct sk_buff *skb;
long timeo;
int err;
timeo = sock_sndtimeo(sk, noblock);
for (;;) {
err = sock_error(sk);
if (err != 0)
goto failure;
err = -EPIPE;
if (sk->sk_shutdown & SEND_SHUTDOWN)
goto failure;
if (sk_wmem_alloc_get(sk) < READ_ONCE(sk->sk_sndbuf))
break;
sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
err = -EAGAIN;
if (!timeo)
goto failure;
if (signal_pending(current))
goto interrupted;
timeo = sock_wait_for_wmem(sk, timeo);
}
skb = alloc_skb_with_frags(header_len, data_len, max_page_order,
errcode, sk->sk_allocation);
if (skb)
skb_set_owner_w(skb, sk);
return skb;
interrupted:
err = sock_intr_errno(timeo);
failure:
*errcode = err;
return NULL;
}
EXPORT_SYMBOL(sock_alloc_send_pskb);
struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size,
int noblock, int *errcode)
{
return sock_alloc_send_pskb(sk, size, 0, noblock, errcode, 0);
}
EXPORT_SYMBOL(sock_alloc_send_skb);
int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg,
struct sockcm_cookie *sockc)
{
u32 tsflags;
switch (cmsg->cmsg_type) {
case SO_MARK:
if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
return -EPERM;
if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32)))
return -EINVAL;
sockc->mark = *(u32 *)CMSG_DATA(cmsg);
break;
case SO_TIMESTAMPING_OLD:
if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32)))
return -EINVAL;
tsflags = *(u32 *)CMSG_DATA(cmsg);
if (tsflags & ~SOF_TIMESTAMPING_TX_RECORD_MASK)
return -EINVAL;
sockc->tsflags &= ~SOF_TIMESTAMPING_TX_RECORD_MASK;
sockc->tsflags |= tsflags;
break;
case SCM_TXTIME:
if (!sock_flag(sk, SOCK_TXTIME))
return -EINVAL;
if (cmsg->cmsg_len != CMSG_LEN(sizeof(u64)))
return -EINVAL;
sockc->transmit_time = get_unaligned((u64 *)CMSG_DATA(cmsg));
break;
/* SCM_RIGHTS and SCM_CREDENTIALS are semantically in SOL_UNIX. */
case SCM_RIGHTS:
case SCM_CREDENTIALS:
break;
default:
return -EINVAL;
}
return 0;
}
EXPORT_SYMBOL(__sock_cmsg_send);
int sock_cmsg_send(struct sock *sk, struct msghdr *msg,
struct sockcm_cookie *sockc)
{
struct cmsghdr *cmsg;
int ret;
for_each_cmsghdr(cmsg, msg) {
if (!CMSG_OK(msg, cmsg))
return -EINVAL;
if (cmsg->cmsg_level != SOL_SOCKET)
continue;
ret = __sock_cmsg_send(sk, msg, cmsg, sockc);
if (ret)
return ret;
}
return 0;
}
EXPORT_SYMBOL(sock_cmsg_send);
static void sk_enter_memory_pressure(struct sock *sk)
{
if (!sk->sk_prot->enter_memory_pressure)
return;
sk->sk_prot->enter_memory_pressure(sk);
}
static void sk_leave_memory_pressure(struct sock *sk)
{
if (sk->sk_prot->leave_memory_pressure) {
sk->sk_prot->leave_memory_pressure(sk);
} else {
unsigned long *memory_pressure = sk->sk_prot->memory_pressure;
if (memory_pressure && READ_ONCE(*memory_pressure))
WRITE_ONCE(*memory_pressure, 0);
}
}
net: use a per task frag allocator We currently use a per socket order-0 page cache for tcp_sendmsg() operations. This page is used to build fragments for skbs. Its done to increase probability of coalescing small write() into single segments in skbs still in write queue (not yet sent) But it wastes a lot of memory for applications handling many mostly idle sockets, since each socket holds one page in sk->sk_sndmsg_page Its also quite inefficient to build TSO 64KB packets, because we need about 16 pages per skb on arches where PAGE_SIZE = 4096, so we hit page allocator more than wanted. This patch adds a per task frag allocator and uses bigger pages, if available. An automatic fallback is done in case of memory pressure. (up to 32768 bytes per frag, thats order-3 pages on x86) This increases TCP stream performance by 20% on loopback device, but also benefits on other network devices, since 8x less frags are mapped on transmit and unmapped on tx completion. Alexander Duyck mentioned a probable performance win on systems with IOMMU enabled. Its possible some SG enabled hardware cant cope with bigger fragments, but their ndo_start_xmit() should already handle this, splitting a fragment in sub fragments, since some arches have PAGE_SIZE=65536 Successfully tested on various ethernet devices. (ixgbe, igb, bnx2x, tg3, mellanox mlx4) Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Ben Hutchings <bhutchings@solarflare.com> Cc: Vijay Subramanian <subramanian.vijay@gmail.com> Cc: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Vijay Subramanian <subramanian.vijay@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-23 23:04:42 +00:00
#define SKB_FRAG_PAGE_ORDER get_order(32768)
net: add high_order_alloc_disable sysctl/static key >From linux-3.7, (commit 5640f7685831 "net: use a per task frag allocator") TCP sendmsg() has preferred using order-3 allocations. While it gives good results for most cases, we had reports that heavy uses of TCP over loopback were hitting a spinlock contention in page allocations/freeing. This commits adds a sysctl so that admins can opt-in for order-0 allocations. Hopefully mm layer might optimize order-3 allocations in the future since it could give us a nice boost (see 8 lines of following benchmark) The following benchmark shows a win when more than 8 TCP_STREAM threads are running (56 x86 cores server in my tests) for thr in {1..30} do sysctl -wq net.core.high_order_alloc_disable=0 T0=`./super_netperf $thr -H 127.0.0.1 -l 15` sysctl -wq net.core.high_order_alloc_disable=1 T1=`./super_netperf $thr -H 127.0.0.1 -l 15` echo $thr:$T0:$T1 done 1: 49979: 37267 2: 98745: 76286 3: 141088: 110051 4: 177414: 144772 5: 197587: 173563 6: 215377: 208448 7: 241061: 234087 8: 267155: 263373 9: 295069: 297402 10: 312393: 335213 11: 340462: 368778 12: 371366: 403954 13: 412344: 443713 14: 426617: 473580 15: 474418: 507861 16: 503261: 538539 17: 522331: 563096 18: 532409: 567084 19: 550824: 605240 20: 525493: 641988 21: 564574: 665843 22: 567349: 690868 23: 583846: 710917 24: 588715: 736306 25: 603212: 763494 26: 604083: 792654 27: 602241: 796450 28: 604291: 797993 29: 611610: 833249 30: 577356: 841062 Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-14 23:22:21 +00:00
DEFINE_STATIC_KEY_FALSE(net_high_order_alloc_disable_key);
net: use a per task frag allocator We currently use a per socket order-0 page cache for tcp_sendmsg() operations. This page is used to build fragments for skbs. Its done to increase probability of coalescing small write() into single segments in skbs still in write queue (not yet sent) But it wastes a lot of memory for applications handling many mostly idle sockets, since each socket holds one page in sk->sk_sndmsg_page Its also quite inefficient to build TSO 64KB packets, because we need about 16 pages per skb on arches where PAGE_SIZE = 4096, so we hit page allocator more than wanted. This patch adds a per task frag allocator and uses bigger pages, if available. An automatic fallback is done in case of memory pressure. (up to 32768 bytes per frag, thats order-3 pages on x86) This increases TCP stream performance by 20% on loopback device, but also benefits on other network devices, since 8x less frags are mapped on transmit and unmapped on tx completion. Alexander Duyck mentioned a probable performance win on systems with IOMMU enabled. Its possible some SG enabled hardware cant cope with bigger fragments, but their ndo_start_xmit() should already handle this, splitting a fragment in sub fragments, since some arches have PAGE_SIZE=65536 Successfully tested on various ethernet devices. (ixgbe, igb, bnx2x, tg3, mellanox mlx4) Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Ben Hutchings <bhutchings@solarflare.com> Cc: Vijay Subramanian <subramanian.vijay@gmail.com> Cc: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Vijay Subramanian <subramanian.vijay@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-23 23:04:42 +00:00
/**
* skb_page_frag_refill - check that a page_frag contains enough room
* @sz: minimum size of the fragment we want to get
* @pfrag: pointer to page_frag
* @gfp: priority for memory allocation
*
* Note: While this allocator tries to use high order pages, there is
* no guarantee that allocations succeed. Therefore, @sz MUST be
* less or equal than PAGE_SIZE.
*/
bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t gfp)
net: use a per task frag allocator We currently use a per socket order-0 page cache for tcp_sendmsg() operations. This page is used to build fragments for skbs. Its done to increase probability of coalescing small write() into single segments in skbs still in write queue (not yet sent) But it wastes a lot of memory for applications handling many mostly idle sockets, since each socket holds one page in sk->sk_sndmsg_page Its also quite inefficient to build TSO 64KB packets, because we need about 16 pages per skb on arches where PAGE_SIZE = 4096, so we hit page allocator more than wanted. This patch adds a per task frag allocator and uses bigger pages, if available. An automatic fallback is done in case of memory pressure. (up to 32768 bytes per frag, thats order-3 pages on x86) This increases TCP stream performance by 20% on loopback device, but also benefits on other network devices, since 8x less frags are mapped on transmit and unmapped on tx completion. Alexander Duyck mentioned a probable performance win on systems with IOMMU enabled. Its possible some SG enabled hardware cant cope with bigger fragments, but their ndo_start_xmit() should already handle this, splitting a fragment in sub fragments, since some arches have PAGE_SIZE=65536 Successfully tested on various ethernet devices. (ixgbe, igb, bnx2x, tg3, mellanox mlx4) Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Ben Hutchings <bhutchings@solarflare.com> Cc: Vijay Subramanian <subramanian.vijay@gmail.com> Cc: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Vijay Subramanian <subramanian.vijay@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-23 23:04:42 +00:00
{
if (pfrag->page) {
2016-03-17 21:19:26 +00:00
if (page_ref_count(pfrag->page) == 1) {
net: use a per task frag allocator We currently use a per socket order-0 page cache for tcp_sendmsg() operations. This page is used to build fragments for skbs. Its done to increase probability of coalescing small write() into single segments in skbs still in write queue (not yet sent) But it wastes a lot of memory for applications handling many mostly idle sockets, since each socket holds one page in sk->sk_sndmsg_page Its also quite inefficient to build TSO 64KB packets, because we need about 16 pages per skb on arches where PAGE_SIZE = 4096, so we hit page allocator more than wanted. This patch adds a per task frag allocator and uses bigger pages, if available. An automatic fallback is done in case of memory pressure. (up to 32768 bytes per frag, thats order-3 pages on x86) This increases TCP stream performance by 20% on loopback device, but also benefits on other network devices, since 8x less frags are mapped on transmit and unmapped on tx completion. Alexander Duyck mentioned a probable performance win on systems with IOMMU enabled. Its possible some SG enabled hardware cant cope with bigger fragments, but their ndo_start_xmit() should already handle this, splitting a fragment in sub fragments, since some arches have PAGE_SIZE=65536 Successfully tested on various ethernet devices. (ixgbe, igb, bnx2x, tg3, mellanox mlx4) Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Ben Hutchings <bhutchings@solarflare.com> Cc: Vijay Subramanian <subramanian.vijay@gmail.com> Cc: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Vijay Subramanian <subramanian.vijay@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-23 23:04:42 +00:00
pfrag->offset = 0;
return true;
}
if (pfrag->offset + sz <= pfrag->size)
net: use a per task frag allocator We currently use a per socket order-0 page cache for tcp_sendmsg() operations. This page is used to build fragments for skbs. Its done to increase probability of coalescing small write() into single segments in skbs still in write queue (not yet sent) But it wastes a lot of memory for applications handling many mostly idle sockets, since each socket holds one page in sk->sk_sndmsg_page Its also quite inefficient to build TSO 64KB packets, because we need about 16 pages per skb on arches where PAGE_SIZE = 4096, so we hit page allocator more than wanted. This patch adds a per task frag allocator and uses bigger pages, if available. An automatic fallback is done in case of memory pressure. (up to 32768 bytes per frag, thats order-3 pages on x86) This increases TCP stream performance by 20% on loopback device, but also benefits on other network devices, since 8x less frags are mapped on transmit and unmapped on tx completion. Alexander Duyck mentioned a probable performance win on systems with IOMMU enabled. Its possible some SG enabled hardware cant cope with bigger fragments, but their ndo_start_xmit() should already handle this, splitting a fragment in sub fragments, since some arches have PAGE_SIZE=65536 Successfully tested on various ethernet devices. (ixgbe, igb, bnx2x, tg3, mellanox mlx4) Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Ben Hutchings <bhutchings@solarflare.com> Cc: Vijay Subramanian <subramanian.vijay@gmail.com> Cc: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Vijay Subramanian <subramanian.vijay@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-23 23:04:42 +00:00
return true;
put_page(pfrag->page);
}
pfrag->offset = 0;
net: add high_order_alloc_disable sysctl/static key >From linux-3.7, (commit 5640f7685831 "net: use a per task frag allocator") TCP sendmsg() has preferred using order-3 allocations. While it gives good results for most cases, we had reports that heavy uses of TCP over loopback were hitting a spinlock contention in page allocations/freeing. This commits adds a sysctl so that admins can opt-in for order-0 allocations. Hopefully mm layer might optimize order-3 allocations in the future since it could give us a nice boost (see 8 lines of following benchmark) The following benchmark shows a win when more than 8 TCP_STREAM threads are running (56 x86 cores server in my tests) for thr in {1..30} do sysctl -wq net.core.high_order_alloc_disable=0 T0=`./super_netperf $thr -H 127.0.0.1 -l 15` sysctl -wq net.core.high_order_alloc_disable=1 T1=`./super_netperf $thr -H 127.0.0.1 -l 15` echo $thr:$T0:$T1 done 1: 49979: 37267 2: 98745: 76286 3: 141088: 110051 4: 177414: 144772 5: 197587: 173563 6: 215377: 208448 7: 241061: 234087 8: 267155: 263373 9: 295069: 297402 10: 312393: 335213 11: 340462: 368778 12: 371366: 403954 13: 412344: 443713 14: 426617: 473580 15: 474418: 507861 16: 503261: 538539 17: 522331: 563096 18: 532409: 567084 19: 550824: 605240 20: 525493: 641988 21: 564574: 665843 22: 567349: 690868 23: 583846: 710917 24: 588715: 736306 25: 603212: 763494 26: 604083: 792654 27: 602241: 796450 28: 604291: 797993 29: 611610: 833249 30: 577356: 841062 Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-14 23:22:21 +00:00
if (SKB_FRAG_PAGE_ORDER &&
!static_branch_unlikely(&net_high_order_alloc_disable_key)) {
mm, page_alloc: distinguish between being unable to sleep, unwilling to sleep and avoiding waking kswapd __GFP_WAIT has been used to identify atomic context in callers that hold spinlocks or are in interrupts. They are expected to be high priority and have access one of two watermarks lower than "min" which can be referred to as the "atomic reserve". __GFP_HIGH users get access to the first lower watermark and can be called the "high priority reserve". Over time, callers had a requirement to not block when fallback options were available. Some have abused __GFP_WAIT leading to a situation where an optimisitic allocation with a fallback option can access atomic reserves. This patch uses __GFP_ATOMIC to identify callers that are truely atomic, cannot sleep and have no alternative. High priority users continue to use __GFP_HIGH. __GFP_DIRECT_RECLAIM identifies callers that can sleep and are willing to enter direct reclaim. __GFP_KSWAPD_RECLAIM to identify callers that want to wake kswapd for background reclaim. __GFP_WAIT is redefined as a caller that is willing to enter direct reclaim and wake kswapd for background reclaim. This patch then converts a number of sites o __GFP_ATOMIC is used by callers that are high priority and have memory pools for those requests. GFP_ATOMIC uses this flag. o Callers that have a limited mempool to guarantee forward progress clear __GFP_DIRECT_RECLAIM but keep __GFP_KSWAPD_RECLAIM. bio allocations fall into this category where kswapd will still be woken but atomic reserves are not used as there is a one-entry mempool to guarantee progress. o Callers that are checking if they are non-blocking should use the helper gfpflags_allow_blocking() where possible. This is because checking for __GFP_WAIT as was done historically now can trigger false positives. Some exceptions like dm-crypt.c exist where the code intent is clearer if __GFP_DIRECT_RECLAIM is used instead of the helper due to flag manipulations. o Callers that built their own GFP flags instead of starting with GFP_KERNEL and friends now also need to specify __GFP_KSWAPD_RECLAIM. The first key hazard to watch out for is callers that removed __GFP_WAIT and was depending on access to atomic reserves for inconspicuous reasons. In some cases it may be appropriate for them to use __GFP_HIGH. The second key hazard is callers that assembled their own combination of GFP flags instead of starting with something like GFP_KERNEL. They may now wish to specify __GFP_KSWAPD_RECLAIM. It's almost certainly harmless if it's missed in most cases as other activity will wake kswapd. Signed-off-by: Mel Gorman <mgorman@techsingularity.net> Acked-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Christoph Lameter <cl@linux.com> Cc: David Rientjes <rientjes@google.com> Cc: Vitaly Wool <vitalywool@gmail.com> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-07 00:28:21 +00:00
/* Avoid direct reclaim but allow kswapd to wake */
pfrag->page = alloc_pages((gfp & ~__GFP_DIRECT_RECLAIM) |
__GFP_COMP | __GFP_NOWARN |
__GFP_NORETRY,
SKB_FRAG_PAGE_ORDER);
net: use a per task frag allocator We currently use a per socket order-0 page cache for tcp_sendmsg() operations. This page is used to build fragments for skbs. Its done to increase probability of coalescing small write() into single segments in skbs still in write queue (not yet sent) But it wastes a lot of memory for applications handling many mostly idle sockets, since each socket holds one page in sk->sk_sndmsg_page Its also quite inefficient to build TSO 64KB packets, because we need about 16 pages per skb on arches where PAGE_SIZE = 4096, so we hit page allocator more than wanted. This patch adds a per task frag allocator and uses bigger pages, if available. An automatic fallback is done in case of memory pressure. (up to 32768 bytes per frag, thats order-3 pages on x86) This increases TCP stream performance by 20% on loopback device, but also benefits on other network devices, since 8x less frags are mapped on transmit and unmapped on tx completion. Alexander Duyck mentioned a probable performance win on systems with IOMMU enabled. Its possible some SG enabled hardware cant cope with bigger fragments, but their ndo_start_xmit() should already handle this, splitting a fragment in sub fragments, since some arches have PAGE_SIZE=65536 Successfully tested on various ethernet devices. (ixgbe, igb, bnx2x, tg3, mellanox mlx4) Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Ben Hutchings <bhutchings@solarflare.com> Cc: Vijay Subramanian <subramanian.vijay@gmail.com> Cc: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Vijay Subramanian <subramanian.vijay@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-23 23:04:42 +00:00
if (likely(pfrag->page)) {
pfrag->size = PAGE_SIZE << SKB_FRAG_PAGE_ORDER;
net: use a per task frag allocator We currently use a per socket order-0 page cache for tcp_sendmsg() operations. This page is used to build fragments for skbs. Its done to increase probability of coalescing small write() into single segments in skbs still in write queue (not yet sent) But it wastes a lot of memory for applications handling many mostly idle sockets, since each socket holds one page in sk->sk_sndmsg_page Its also quite inefficient to build TSO 64KB packets, because we need about 16 pages per skb on arches where PAGE_SIZE = 4096, so we hit page allocator more than wanted. This patch adds a per task frag allocator and uses bigger pages, if available. An automatic fallback is done in case of memory pressure. (up to 32768 bytes per frag, thats order-3 pages on x86) This increases TCP stream performance by 20% on loopback device, but also benefits on other network devices, since 8x less frags are mapped on transmit and unmapped on tx completion. Alexander Duyck mentioned a probable performance win on systems with IOMMU enabled. Its possible some SG enabled hardware cant cope with bigger fragments, but their ndo_start_xmit() should already handle this, splitting a fragment in sub fragments, since some arches have PAGE_SIZE=65536 Successfully tested on various ethernet devices. (ixgbe, igb, bnx2x, tg3, mellanox mlx4) Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Ben Hutchings <bhutchings@solarflare.com> Cc: Vijay Subramanian <subramanian.vijay@gmail.com> Cc: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Vijay Subramanian <subramanian.vijay@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-23 23:04:42 +00:00
return true;
}
}
pfrag->page = alloc_page(gfp);
if (likely(pfrag->page)) {
pfrag->size = PAGE_SIZE;
return true;
}
return false;
}
EXPORT_SYMBOL(skb_page_frag_refill);
bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag)
{
if (likely(skb_page_frag_refill(32U, pfrag, sk->sk_allocation)))
return true;
net: use a per task frag allocator We currently use a per socket order-0 page cache for tcp_sendmsg() operations. This page is used to build fragments for skbs. Its done to increase probability of coalescing small write() into single segments in skbs still in write queue (not yet sent) But it wastes a lot of memory for applications handling many mostly idle sockets, since each socket holds one page in sk->sk_sndmsg_page Its also quite inefficient to build TSO 64KB packets, because we need about 16 pages per skb on arches where PAGE_SIZE = 4096, so we hit page allocator more than wanted. This patch adds a per task frag allocator and uses bigger pages, if available. An automatic fallback is done in case of memory pressure. (up to 32768 bytes per frag, thats order-3 pages on x86) This increases TCP stream performance by 20% on loopback device, but also benefits on other network devices, since 8x less frags are mapped on transmit and unmapped on tx completion. Alexander Duyck mentioned a probable performance win on systems with IOMMU enabled. Its possible some SG enabled hardware cant cope with bigger fragments, but their ndo_start_xmit() should already handle this, splitting a fragment in sub fragments, since some arches have PAGE_SIZE=65536 Successfully tested on various ethernet devices. (ixgbe, igb, bnx2x, tg3, mellanox mlx4) Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Ben Hutchings <bhutchings@solarflare.com> Cc: Vijay Subramanian <subramanian.vijay@gmail.com> Cc: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Vijay Subramanian <subramanian.vijay@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-23 23:04:42 +00:00
sk_enter_memory_pressure(sk);
sk_stream_moderate_sndbuf(sk);
return false;
}
EXPORT_SYMBOL(sk_page_frag_refill);
void __lock_sock(struct sock *sk)
__releases(&sk->sk_lock.slock)
__acquires(&sk->sk_lock.slock)
{
DEFINE_WAIT(wait);
for (;;) {
prepare_to_wait_exclusive(&sk->sk_lock.wq, &wait,
TASK_UNINTERRUPTIBLE);
spin_unlock_bh(&sk->sk_lock.slock);
schedule();
spin_lock_bh(&sk->sk_lock.slock);
if (!sock_owned_by_user(sk))
break;
}
finish_wait(&sk->sk_lock.wq, &wait);
}
void __release_sock(struct sock *sk)
__releases(&sk->sk_lock.slock)
__acquires(&sk->sk_lock.slock)
{
struct sk_buff *skb, *next;
while ((skb = sk->sk_backlog.head) != NULL) {
sk->sk_backlog.head = sk->sk_backlog.tail = NULL;
spin_unlock_bh(&sk->sk_lock.slock);
do {
next = skb->next;
prefetch(next);
WARN_ON_ONCE(skb_dst_is_noref(skb));
skb_mark_not_on_list(skb);
sk_backlog_rcv(sk, skb);
cond_resched();
skb = next;
} while (skb != NULL);
spin_lock_bh(&sk->sk_lock.slock);
}
net: add limit for socket backlog We got system OOM while running some UDP netperf testing on the loopback device. The case is multiple senders sent stream UDP packets to a single receiver via loopback on local host. Of course, the receiver is not able to handle all the packets in time. But we surprisingly found that these packets were not discarded due to the receiver's sk->sk_rcvbuf limit. Instead, they are kept queuing to sk->sk_backlog and finally ate up all the memory. We believe this is a secure hole that a none privileged user can crash the system. The root cause for this problem is, when the receiver is doing __release_sock() (i.e. after userspace recv, kernel udp_recvmsg -> skb_free_datagram_locked -> release_sock), it moves skbs from backlog to sk_receive_queue with the softirq enabled. In the above case, multiple busy senders will almost make it an endless loop. The skbs in the backlog end up eat all the system memory. The issue is not only for UDP. Any protocols using socket backlog is potentially affected. The patch adds limit for socket backlog so that the backlog size cannot be expanded endlessly. Reported-by: Alex Shi <alex.shi@intel.com> Cc: David Miller <davem@davemloft.net> Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Cc: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru Cc: "Pekka Savola (ipv6)" <pekkas@netcore.fi> Cc: Patrick McHardy <kaber@trash.net> Cc: Vlad Yasevich <vladislav.yasevich@hp.com> Cc: Sridhar Samudrala <sri@us.ibm.com> Cc: Jon Maloy <jon.maloy@ericsson.com> Cc: Allan Stephens <allan.stephens@windriver.com> Cc: Andrew Hendry <andrew.hendry@gmail.com> Signed-off-by: Zhu Yi <yi.zhu@intel.com> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Acked-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-03-04 18:01:40 +00:00
/*
* Doing the zeroing here guarantee we can not loop forever
* while a wild producer attempts to flood us.
*/
sk->sk_backlog.len = 0;
}
tcp: make tcp_sendmsg() aware of socket backlog Large sendmsg()/write() hold socket lock for the duration of the call, unless sk->sk_sndbuf limit is hit. This is bad because incoming packets are parked into socket backlog for a long time. Critical decisions like fast retransmit might be delayed. Receivers have to maintain a big out of order queue with additional cpu overhead, and also possible stalls in TX once windows are full. Bidirectional flows are particularly hurt since the backlog can become quite big if the copy from user space triggers IO (page faults) Some applications learnt to use sendmsg() (or sendmmsg()) with small chunks to avoid this issue. Kernel should know better, right ? Add a generic sk_flush_backlog() helper and use it right before a new skb is allocated. Typically we put 64KB of payload per skb (unless MSG_EOR is requested) and checking socket backlog every 64KB gives good results. As a matter of fact, tests with TSO/GSO disabled give very nice results, as we manage to keep a small write queue and smaller perceived rtt. Note that sk_flush_backlog() maintains socket ownership, so is not equivalent to a {release_sock(sk); lock_sock(sk);}, to ensure implicit atomicity rules that sendmsg() was giving to (possibly buggy) applications. In this simple implementation, I chose to not call tcp_release_cb(), but we might consider this later. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Alexei Starovoitov <ast@fb.com> Cc: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Acked-by: Soheil Hassas Yeganeh <soheil@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-29 21:16:53 +00:00
void __sk_flush_backlog(struct sock *sk)
{
spin_lock_bh(&sk->sk_lock.slock);
__release_sock(sk);
spin_unlock_bh(&sk->sk_lock.slock);
}
/**
* sk_wait_data - wait for data to arrive at sk_receive_queue
[PATCH] DocBook: changes and extensions to the kernel documentation I have recompiled Linux kernel 2.6.11.5 documentation for me and our university students again. The documentation could be extended for more sources which are equipped by structured comments for recent 2.6 kernels. I have tried to proceed with that task. I have done that more times from 2.6.0 time and it gets boring to do same changes again and again. Linux kernel compiles after changes for i386 and ARM targets. I have added references to some more files into kernel-api book, I have added some section names as well. So please, check that changes do not break something and that categories are not too much skewed. I have changed kernel-doc to accept "fastcall" and "asmlinkage" words reserved by kernel convention. Most of the other changes are modifications in the comments to make kernel-doc happy, accept some parameters description and do not bail out on errors. Changed <pid> to @pid in the description, moved some #ifdef before comments to correct function to comments bindings, etc. You can see result of the modified documentation build at http://cmp.felk.cvut.cz/~pisa/linux/lkdb-2.6.11.tar.gz Some more sources are ready to be included into kernel-doc generated documentation. Sources has been added into kernel-api for now. Some more section names added and probably some more chaos introduced as result of quick cleanup work. Signed-off-by: Pavel Pisa <pisa@cmp.felk.cvut.cz> Signed-off-by: Martin Waitz <tali@admingilde.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-05-01 15:59:25 +00:00
* @sk: sock to wait on
* @timeo: for how long
* @skb: last skb seen on sk_receive_queue
*
* Now socket state including sk->sk_err is changed only under lock,
* hence we may omit checks after joining wait queue.
* We check receive queue before schedule() only as optimization;
* it is very likely that release_sock() added new data.
*/
int sk_wait_data(struct sock *sk, long *timeo, const struct sk_buff *skb)
{
DEFINE_WAIT_FUNC(wait, woken_wake_function);
int rc;
add_wait_queue(sk_sleep(sk), &wait);
sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
rc = sk_wait_event(sk, timeo, skb_peek_tail(&sk->sk_receive_queue) != skb, &wait);
sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
remove_wait_queue(sk_sleep(sk), &wait);
return rc;
}
EXPORT_SYMBOL(sk_wait_data);
[NET] CORE: Introducing new memory accounting interface. This patch introduces new memory accounting functions for each network protocol. Most of them are renamed from memory accounting functions for stream protocols. At the same time, some stream memory accounting functions are removed since other functions do same thing. Renaming: sk_stream_free_skb() -> sk_wmem_free_skb() __sk_stream_mem_reclaim() -> __sk_mem_reclaim() sk_stream_mem_reclaim() -> sk_mem_reclaim() sk_stream_mem_schedule -> __sk_mem_schedule() sk_stream_pages() -> sk_mem_pages() sk_stream_rmem_schedule() -> sk_rmem_schedule() sk_stream_wmem_schedule() -> sk_wmem_schedule() sk_charge_skb() -> sk_mem_charge() Removeing sk_stream_rfree(): consolidates into sock_rfree() sk_stream_set_owner_r(): consolidates into skb_set_owner_r() sk_stream_mem_schedule() The following functions are added. sk_has_account(): check if the protocol supports accounting sk_mem_uncharge(): do the opposite of sk_mem_charge() In addition, to achieve consolidation, updating sk_wmem_queued is removed from sk_mem_charge(). Next, to consolidate memory accounting functions, this patch adds memory accounting calls to network core functions. Moreover, present memory accounting call is renamed to new accounting call. Finally we replace present memory accounting calls with new interface in TCP and SCTP. Signed-off-by: Takahiro Yasui <tyasui@redhat.com> Signed-off-by: Hideo Aoki <haoki@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-31 08:11:19 +00:00
/**
* __sk_mem_raise_allocated - increase memory_allocated
[NET] CORE: Introducing new memory accounting interface. This patch introduces new memory accounting functions for each network protocol. Most of them are renamed from memory accounting functions for stream protocols. At the same time, some stream memory accounting functions are removed since other functions do same thing. Renaming: sk_stream_free_skb() -> sk_wmem_free_skb() __sk_stream_mem_reclaim() -> __sk_mem_reclaim() sk_stream_mem_reclaim() -> sk_mem_reclaim() sk_stream_mem_schedule -> __sk_mem_schedule() sk_stream_pages() -> sk_mem_pages() sk_stream_rmem_schedule() -> sk_rmem_schedule() sk_stream_wmem_schedule() -> sk_wmem_schedule() sk_charge_skb() -> sk_mem_charge() Removeing sk_stream_rfree(): consolidates into sock_rfree() sk_stream_set_owner_r(): consolidates into skb_set_owner_r() sk_stream_mem_schedule() The following functions are added. sk_has_account(): check if the protocol supports accounting sk_mem_uncharge(): do the opposite of sk_mem_charge() In addition, to achieve consolidation, updating sk_wmem_queued is removed from sk_mem_charge(). Next, to consolidate memory accounting functions, this patch adds memory accounting calls to network core functions. Moreover, present memory accounting call is renamed to new accounting call. Finally we replace present memory accounting calls with new interface in TCP and SCTP. Signed-off-by: Takahiro Yasui <tyasui@redhat.com> Signed-off-by: Hideo Aoki <haoki@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-31 08:11:19 +00:00
* @sk: socket
* @size: memory size to allocate
* @amt: pages to allocate
[NET] CORE: Introducing new memory accounting interface. This patch introduces new memory accounting functions for each network protocol. Most of them are renamed from memory accounting functions for stream protocols. At the same time, some stream memory accounting functions are removed since other functions do same thing. Renaming: sk_stream_free_skb() -> sk_wmem_free_skb() __sk_stream_mem_reclaim() -> __sk_mem_reclaim() sk_stream_mem_reclaim() -> sk_mem_reclaim() sk_stream_mem_schedule -> __sk_mem_schedule() sk_stream_pages() -> sk_mem_pages() sk_stream_rmem_schedule() -> sk_rmem_schedule() sk_stream_wmem_schedule() -> sk_wmem_schedule() sk_charge_skb() -> sk_mem_charge() Removeing sk_stream_rfree(): consolidates into sock_rfree() sk_stream_set_owner_r(): consolidates into skb_set_owner_r() sk_stream_mem_schedule() The following functions are added. sk_has_account(): check if the protocol supports accounting sk_mem_uncharge(): do the opposite of sk_mem_charge() In addition, to achieve consolidation, updating sk_wmem_queued is removed from sk_mem_charge(). Next, to consolidate memory accounting functions, this patch adds memory accounting calls to network core functions. Moreover, present memory accounting call is renamed to new accounting call. Finally we replace present memory accounting calls with new interface in TCP and SCTP. Signed-off-by: Takahiro Yasui <tyasui@redhat.com> Signed-off-by: Hideo Aoki <haoki@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-31 08:11:19 +00:00
* @kind: allocation type
*
* Similar to __sk_mem_schedule(), but does not update sk_forward_alloc
[NET] CORE: Introducing new memory accounting interface. This patch introduces new memory accounting functions for each network protocol. Most of them are renamed from memory accounting functions for stream protocols. At the same time, some stream memory accounting functions are removed since other functions do same thing. Renaming: sk_stream_free_skb() -> sk_wmem_free_skb() __sk_stream_mem_reclaim() -> __sk_mem_reclaim() sk_stream_mem_reclaim() -> sk_mem_reclaim() sk_stream_mem_schedule -> __sk_mem_schedule() sk_stream_pages() -> sk_mem_pages() sk_stream_rmem_schedule() -> sk_rmem_schedule() sk_stream_wmem_schedule() -> sk_wmem_schedule() sk_charge_skb() -> sk_mem_charge() Removeing sk_stream_rfree(): consolidates into sock_rfree() sk_stream_set_owner_r(): consolidates into skb_set_owner_r() sk_stream_mem_schedule() The following functions are added. sk_has_account(): check if the protocol supports accounting sk_mem_uncharge(): do the opposite of sk_mem_charge() In addition, to achieve consolidation, updating sk_wmem_queued is removed from sk_mem_charge(). Next, to consolidate memory accounting functions, this patch adds memory accounting calls to network core functions. Moreover, present memory accounting call is renamed to new accounting call. Finally we replace present memory accounting calls with new interface in TCP and SCTP. Signed-off-by: Takahiro Yasui <tyasui@redhat.com> Signed-off-by: Hideo Aoki <haoki@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-31 08:11:19 +00:00
*/
int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind)
[NET] CORE: Introducing new memory accounting interface. This patch introduces new memory accounting functions for each network protocol. Most of them are renamed from memory accounting functions for stream protocols. At the same time, some stream memory accounting functions are removed since other functions do same thing. Renaming: sk_stream_free_skb() -> sk_wmem_free_skb() __sk_stream_mem_reclaim() -> __sk_mem_reclaim() sk_stream_mem_reclaim() -> sk_mem_reclaim() sk_stream_mem_schedule -> __sk_mem_schedule() sk_stream_pages() -> sk_mem_pages() sk_stream_rmem_schedule() -> sk_rmem_schedule() sk_stream_wmem_schedule() -> sk_wmem_schedule() sk_charge_skb() -> sk_mem_charge() Removeing sk_stream_rfree(): consolidates into sock_rfree() sk_stream_set_owner_r(): consolidates into skb_set_owner_r() sk_stream_mem_schedule() The following functions are added. sk_has_account(): check if the protocol supports accounting sk_mem_uncharge(): do the opposite of sk_mem_charge() In addition, to achieve consolidation, updating sk_wmem_queued is removed from sk_mem_charge(). Next, to consolidate memory accounting functions, this patch adds memory accounting calls to network core functions. Moreover, present memory accounting call is renamed to new accounting call. Finally we replace present memory accounting calls with new interface in TCP and SCTP. Signed-off-by: Takahiro Yasui <tyasui@redhat.com> Signed-off-by: Hideo Aoki <haoki@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-31 08:11:19 +00:00
{
struct proto *prot = sk->sk_prot;
long allocated = sk_memory_allocated_add(sk, amt);
bool charged = true;
net: tcp_memcontrol: sanitize tcp memory accounting callbacks There won't be a tcp control soft limit, so integrating the memcg code into the global skmem limiting scheme complicates things unnecessarily. Replace this with simple and clear charge and uncharge calls--hidden behind a jump label--to account skb memory. Note that this is not purely aesthetic: as a result of shoehorning the per-memcg code into the same memory accounting functions that handle the global level, the old code would compare the per-memcg consumption against the smaller of the per-memcg limit and the global limit. This allowed the total consumption of multiple sockets to exceed the global limit, as long as the individual sockets stayed within bounds. After this change, the code will always compare the per-memcg consumption to the per-memcg limit, and the global consumption to the global limit, and thus close this loophole. Without a soft limit, the per-memcg memory pressure state in sockets is generally questionable. However, we did it until now, so we continue to enter it when the hard limit is hit, and packets are dropped, to let other sockets in the cgroup know that they shouldn't grow their transmit windows, either. However, keep it simple in the new callback model and leave memory pressure lazily when the next packet is accepted (as opposed to doing it synchroneously when packets are processed). When packets are dropped, network performance will already be in the toilet, so that should be a reasonable trade-off. As described above, consumption is now checked on the per-memcg level and the global level separately. Likewise, memory pressure states are maintained on both the per-memcg level and the global level, and a socket is considered under pressure when either level asserts as much. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Vladimir Davydov <vdavydov@virtuozzo.com> Acked-by: David S. Miller <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-14 23:21:14 +00:00
if (mem_cgroup_sockets_enabled && sk->sk_memcg &&
!(charged = mem_cgroup_charge_skmem(sk->sk_memcg, amt)))
net: tcp_memcontrol: sanitize tcp memory accounting callbacks There won't be a tcp control soft limit, so integrating the memcg code into the global skmem limiting scheme complicates things unnecessarily. Replace this with simple and clear charge and uncharge calls--hidden behind a jump label--to account skb memory. Note that this is not purely aesthetic: as a result of shoehorning the per-memcg code into the same memory accounting functions that handle the global level, the old code would compare the per-memcg consumption against the smaller of the per-memcg limit and the global limit. This allowed the total consumption of multiple sockets to exceed the global limit, as long as the individual sockets stayed within bounds. After this change, the code will always compare the per-memcg consumption to the per-memcg limit, and the global consumption to the global limit, and thus close this loophole. Without a soft limit, the per-memcg memory pressure state in sockets is generally questionable. However, we did it until now, so we continue to enter it when the hard limit is hit, and packets are dropped, to let other sockets in the cgroup know that they shouldn't grow their transmit windows, either. However, keep it simple in the new callback model and leave memory pressure lazily when the next packet is accepted (as opposed to doing it synchroneously when packets are processed). When packets are dropped, network performance will already be in the toilet, so that should be a reasonable trade-off. As described above, consumption is now checked on the per-memcg level and the global level separately. Likewise, memory pressure states are maintained on both the per-memcg level and the global level, and a socket is considered under pressure when either level asserts as much. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Vladimir Davydov <vdavydov@virtuozzo.com> Acked-by: David S. Miller <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-14 23:21:14 +00:00
goto suppress_allocation;
[NET] CORE: Introducing new memory accounting interface. This patch introduces new memory accounting functions for each network protocol. Most of them are renamed from memory accounting functions for stream protocols. At the same time, some stream memory accounting functions are removed since other functions do same thing. Renaming: sk_stream_free_skb() -> sk_wmem_free_skb() __sk_stream_mem_reclaim() -> __sk_mem_reclaim() sk_stream_mem_reclaim() -> sk_mem_reclaim() sk_stream_mem_schedule -> __sk_mem_schedule() sk_stream_pages() -> sk_mem_pages() sk_stream_rmem_schedule() -> sk_rmem_schedule() sk_stream_wmem_schedule() -> sk_wmem_schedule() sk_charge_skb() -> sk_mem_charge() Removeing sk_stream_rfree(): consolidates into sock_rfree() sk_stream_set_owner_r(): consolidates into skb_set_owner_r() sk_stream_mem_schedule() The following functions are added. sk_has_account(): check if the protocol supports accounting sk_mem_uncharge(): do the opposite of sk_mem_charge() In addition, to achieve consolidation, updating sk_wmem_queued is removed from sk_mem_charge(). Next, to consolidate memory accounting functions, this patch adds memory accounting calls to network core functions. Moreover, present memory accounting call is renamed to new accounting call. Finally we replace present memory accounting calls with new interface in TCP and SCTP. Signed-off-by: Takahiro Yasui <tyasui@redhat.com> Signed-off-by: Hideo Aoki <haoki@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-31 08:11:19 +00:00
/* Under limit. */
net: tcp_memcontrol: sanitize tcp memory accounting callbacks There won't be a tcp control soft limit, so integrating the memcg code into the global skmem limiting scheme complicates things unnecessarily. Replace this with simple and clear charge and uncharge calls--hidden behind a jump label--to account skb memory. Note that this is not purely aesthetic: as a result of shoehorning the per-memcg code into the same memory accounting functions that handle the global level, the old code would compare the per-memcg consumption against the smaller of the per-memcg limit and the global limit. This allowed the total consumption of multiple sockets to exceed the global limit, as long as the individual sockets stayed within bounds. After this change, the code will always compare the per-memcg consumption to the per-memcg limit, and the global consumption to the global limit, and thus close this loophole. Without a soft limit, the per-memcg memory pressure state in sockets is generally questionable. However, we did it until now, so we continue to enter it when the hard limit is hit, and packets are dropped, to let other sockets in the cgroup know that they shouldn't grow their transmit windows, either. However, keep it simple in the new callback model and leave memory pressure lazily when the next packet is accepted (as opposed to doing it synchroneously when packets are processed). When packets are dropped, network performance will already be in the toilet, so that should be a reasonable trade-off. As described above, consumption is now checked on the per-memcg level and the global level separately. Likewise, memory pressure states are maintained on both the per-memcg level and the global level, and a socket is considered under pressure when either level asserts as much. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Vladimir Davydov <vdavydov@virtuozzo.com> Acked-by: David S. Miller <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-14 23:21:14 +00:00
if (allocated <= sk_prot_mem_limits(sk, 0)) {
sk_leave_memory_pressure(sk);
[NET] CORE: Introducing new memory accounting interface. This patch introduces new memory accounting functions for each network protocol. Most of them are renamed from memory accounting functions for stream protocols. At the same time, some stream memory accounting functions are removed since other functions do same thing. Renaming: sk_stream_free_skb() -> sk_wmem_free_skb() __sk_stream_mem_reclaim() -> __sk_mem_reclaim() sk_stream_mem_reclaim() -> sk_mem_reclaim() sk_stream_mem_schedule -> __sk_mem_schedule() sk_stream_pages() -> sk_mem_pages() sk_stream_rmem_schedule() -> sk_rmem_schedule() sk_stream_wmem_schedule() -> sk_wmem_schedule() sk_charge_skb() -> sk_mem_charge() Removeing sk_stream_rfree(): consolidates into sock_rfree() sk_stream_set_owner_r(): consolidates into skb_set_owner_r() sk_stream_mem_schedule() The following functions are added. sk_has_account(): check if the protocol supports accounting sk_mem_uncharge(): do the opposite of sk_mem_charge() In addition, to achieve consolidation, updating sk_wmem_queued is removed from sk_mem_charge(). Next, to consolidate memory accounting functions, this patch adds memory accounting calls to network core functions. Moreover, present memory accounting call is renamed to new accounting call. Finally we replace present memory accounting calls with new interface in TCP and SCTP. Signed-off-by: Takahiro Yasui <tyasui@redhat.com> Signed-off-by: Hideo Aoki <haoki@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-31 08:11:19 +00:00
return 1;
}
net: tcp_memcontrol: sanitize tcp memory accounting callbacks There won't be a tcp control soft limit, so integrating the memcg code into the global skmem limiting scheme complicates things unnecessarily. Replace this with simple and clear charge and uncharge calls--hidden behind a jump label--to account skb memory. Note that this is not purely aesthetic: as a result of shoehorning the per-memcg code into the same memory accounting functions that handle the global level, the old code would compare the per-memcg consumption against the smaller of the per-memcg limit and the global limit. This allowed the total consumption of multiple sockets to exceed the global limit, as long as the individual sockets stayed within bounds. After this change, the code will always compare the per-memcg consumption to the per-memcg limit, and the global consumption to the global limit, and thus close this loophole. Without a soft limit, the per-memcg memory pressure state in sockets is generally questionable. However, we did it until now, so we continue to enter it when the hard limit is hit, and packets are dropped, to let other sockets in the cgroup know that they shouldn't grow their transmit windows, either. However, keep it simple in the new callback model and leave memory pressure lazily when the next packet is accepted (as opposed to doing it synchroneously when packets are processed). When packets are dropped, network performance will already be in the toilet, so that should be a reasonable trade-off. As described above, consumption is now checked on the per-memcg level and the global level separately. Likewise, memory pressure states are maintained on both the per-memcg level and the global level, and a socket is considered under pressure when either level asserts as much. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Vladimir Davydov <vdavydov@virtuozzo.com> Acked-by: David S. Miller <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-14 23:21:14 +00:00
/* Under pressure. */
if (allocated > sk_prot_mem_limits(sk, 1))
sk_enter_memory_pressure(sk);
[NET] CORE: Introducing new memory accounting interface. This patch introduces new memory accounting functions for each network protocol. Most of them are renamed from memory accounting functions for stream protocols. At the same time, some stream memory accounting functions are removed since other functions do same thing. Renaming: sk_stream_free_skb() -> sk_wmem_free_skb() __sk_stream_mem_reclaim() -> __sk_mem_reclaim() sk_stream_mem_reclaim() -> sk_mem_reclaim() sk_stream_mem_schedule -> __sk_mem_schedule() sk_stream_pages() -> sk_mem_pages() sk_stream_rmem_schedule() -> sk_rmem_schedule() sk_stream_wmem_schedule() -> sk_wmem_schedule() sk_charge_skb() -> sk_mem_charge() Removeing sk_stream_rfree(): consolidates into sock_rfree() sk_stream_set_owner_r(): consolidates into skb_set_owner_r() sk_stream_mem_schedule() The following functions are added. sk_has_account(): check if the protocol supports accounting sk_mem_uncharge(): do the opposite of sk_mem_charge() In addition, to achieve consolidation, updating sk_wmem_queued is removed from sk_mem_charge(). Next, to consolidate memory accounting functions, this patch adds memory accounting calls to network core functions. Moreover, present memory accounting call is renamed to new accounting call. Finally we replace present memory accounting calls with new interface in TCP and SCTP. Signed-off-by: Takahiro Yasui <tyasui@redhat.com> Signed-off-by: Hideo Aoki <haoki@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-31 08:11:19 +00:00
net: tcp_memcontrol: sanitize tcp memory accounting callbacks There won't be a tcp control soft limit, so integrating the memcg code into the global skmem limiting scheme complicates things unnecessarily. Replace this with simple and clear charge and uncharge calls--hidden behind a jump label--to account skb memory. Note that this is not purely aesthetic: as a result of shoehorning the per-memcg code into the same memory accounting functions that handle the global level, the old code would compare the per-memcg consumption against the smaller of the per-memcg limit and the global limit. This allowed the total consumption of multiple sockets to exceed the global limit, as long as the individual sockets stayed within bounds. After this change, the code will always compare the per-memcg consumption to the per-memcg limit, and the global consumption to the global limit, and thus close this loophole. Without a soft limit, the per-memcg memory pressure state in sockets is generally questionable. However, we did it until now, so we continue to enter it when the hard limit is hit, and packets are dropped, to let other sockets in the cgroup know that they shouldn't grow their transmit windows, either. However, keep it simple in the new callback model and leave memory pressure lazily when the next packet is accepted (as opposed to doing it synchroneously when packets are processed). When packets are dropped, network performance will already be in the toilet, so that should be a reasonable trade-off. As described above, consumption is now checked on the per-memcg level and the global level separately. Likewise, memory pressure states are maintained on both the per-memcg level and the global level, and a socket is considered under pressure when either level asserts as much. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Vladimir Davydov <vdavydov@virtuozzo.com> Acked-by: David S. Miller <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-14 23:21:14 +00:00
/* Over hard limit. */
if (allocated > sk_prot_mem_limits(sk, 2))
[NET] CORE: Introducing new memory accounting interface. This patch introduces new memory accounting functions for each network protocol. Most of them are renamed from memory accounting functions for stream protocols. At the same time, some stream memory accounting functions are removed since other functions do same thing. Renaming: sk_stream_free_skb() -> sk_wmem_free_skb() __sk_stream_mem_reclaim() -> __sk_mem_reclaim() sk_stream_mem_reclaim() -> sk_mem_reclaim() sk_stream_mem_schedule -> __sk_mem_schedule() sk_stream_pages() -> sk_mem_pages() sk_stream_rmem_schedule() -> sk_rmem_schedule() sk_stream_wmem_schedule() -> sk_wmem_schedule() sk_charge_skb() -> sk_mem_charge() Removeing sk_stream_rfree(): consolidates into sock_rfree() sk_stream_set_owner_r(): consolidates into skb_set_owner_r() sk_stream_mem_schedule() The following functions are added. sk_has_account(): check if the protocol supports accounting sk_mem_uncharge(): do the opposite of sk_mem_charge() In addition, to achieve consolidation, updating sk_wmem_queued is removed from sk_mem_charge(). Next, to consolidate memory accounting functions, this patch adds memory accounting calls to network core functions. Moreover, present memory accounting call is renamed to new accounting call. Finally we replace present memory accounting calls with new interface in TCP and SCTP. Signed-off-by: Takahiro Yasui <tyasui@redhat.com> Signed-off-by: Hideo Aoki <haoki@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-31 08:11:19 +00:00
goto suppress_allocation;
/* guarantee minimum buffer size under pressure */
if (kind == SK_MEM_RECV) {
if (atomic_read(&sk->sk_rmem_alloc) < sk_get_rmem0(sk, prot))
[NET] CORE: Introducing new memory accounting interface. This patch introduces new memory accounting functions for each network protocol. Most of them are renamed from memory accounting functions for stream protocols. At the same time, some stream memory accounting functions are removed since other functions do same thing. Renaming: sk_stream_free_skb() -> sk_wmem_free_skb() __sk_stream_mem_reclaim() -> __sk_mem_reclaim() sk_stream_mem_reclaim() -> sk_mem_reclaim() sk_stream_mem_schedule -> __sk_mem_schedule() sk_stream_pages() -> sk_mem_pages() sk_stream_rmem_schedule() -> sk_rmem_schedule() sk_stream_wmem_schedule() -> sk_wmem_schedule() sk_charge_skb() -> sk_mem_charge() Removeing sk_stream_rfree(): consolidates into sock_rfree() sk_stream_set_owner_r(): consolidates into skb_set_owner_r() sk_stream_mem_schedule() The following functions are added. sk_has_account(): check if the protocol supports accounting sk_mem_uncharge(): do the opposite of sk_mem_charge() In addition, to achieve consolidation, updating sk_wmem_queued is removed from sk_mem_charge(). Next, to consolidate memory accounting functions, this patch adds memory accounting calls to network core functions. Moreover, present memory accounting call is renamed to new accounting call. Finally we replace present memory accounting calls with new interface in TCP and SCTP. Signed-off-by: Takahiro Yasui <tyasui@redhat.com> Signed-off-by: Hideo Aoki <haoki@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-31 08:11:19 +00:00
return 1;
[NET] CORE: Introducing new memory accounting interface. This patch introduces new memory accounting functions for each network protocol. Most of them are renamed from memory accounting functions for stream protocols. At the same time, some stream memory accounting functions are removed since other functions do same thing. Renaming: sk_stream_free_skb() -> sk_wmem_free_skb() __sk_stream_mem_reclaim() -> __sk_mem_reclaim() sk_stream_mem_reclaim() -> sk_mem_reclaim() sk_stream_mem_schedule -> __sk_mem_schedule() sk_stream_pages() -> sk_mem_pages() sk_stream_rmem_schedule() -> sk_rmem_schedule() sk_stream_wmem_schedule() -> sk_wmem_schedule() sk_charge_skb() -> sk_mem_charge() Removeing sk_stream_rfree(): consolidates into sock_rfree() sk_stream_set_owner_r(): consolidates into skb_set_owner_r() sk_stream_mem_schedule() The following functions are added. sk_has_account(): check if the protocol supports accounting sk_mem_uncharge(): do the opposite of sk_mem_charge() In addition, to achieve consolidation, updating sk_wmem_queued is removed from sk_mem_charge(). Next, to consolidate memory accounting functions, this patch adds memory accounting calls to network core functions. Moreover, present memory accounting call is renamed to new accounting call. Finally we replace present memory accounting calls with new interface in TCP and SCTP. Signed-off-by: Takahiro Yasui <tyasui@redhat.com> Signed-off-by: Hideo Aoki <haoki@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-31 08:11:19 +00:00
} else { /* SK_MEM_SEND */
int wmem0 = sk_get_wmem0(sk, prot);
[NET] CORE: Introducing new memory accounting interface. This patch introduces new memory accounting functions for each network protocol. Most of them are renamed from memory accounting functions for stream protocols. At the same time, some stream memory accounting functions are removed since other functions do same thing. Renaming: sk_stream_free_skb() -> sk_wmem_free_skb() __sk_stream_mem_reclaim() -> __sk_mem_reclaim() sk_stream_mem_reclaim() -> sk_mem_reclaim() sk_stream_mem_schedule -> __sk_mem_schedule() sk_stream_pages() -> sk_mem_pages() sk_stream_rmem_schedule() -> sk_rmem_schedule() sk_stream_wmem_schedule() -> sk_wmem_schedule() sk_charge_skb() -> sk_mem_charge() Removeing sk_stream_rfree(): consolidates into sock_rfree() sk_stream_set_owner_r(): consolidates into skb_set_owner_r() sk_stream_mem_schedule() The following functions are added. sk_has_account(): check if the protocol supports accounting sk_mem_uncharge(): do the opposite of sk_mem_charge() In addition, to achieve consolidation, updating sk_wmem_queued is removed from sk_mem_charge(). Next, to consolidate memory accounting functions, this patch adds memory accounting calls to network core functions. Moreover, present memory accounting call is renamed to new accounting call. Finally we replace present memory accounting calls with new interface in TCP and SCTP. Signed-off-by: Takahiro Yasui <tyasui@redhat.com> Signed-off-by: Hideo Aoki <haoki@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-31 08:11:19 +00:00
if (sk->sk_type == SOCK_STREAM) {
if (sk->sk_wmem_queued < wmem0)
[NET] CORE: Introducing new memory accounting interface. This patch introduces new memory accounting functions for each network protocol. Most of them are renamed from memory accounting functions for stream protocols. At the same time, some stream memory accounting functions are removed since other functions do same thing. Renaming: sk_stream_free_skb() -> sk_wmem_free_skb() __sk_stream_mem_reclaim() -> __sk_mem_reclaim() sk_stream_mem_reclaim() -> sk_mem_reclaim() sk_stream_mem_schedule -> __sk_mem_schedule() sk_stream_pages() -> sk_mem_pages() sk_stream_rmem_schedule() -> sk_rmem_schedule() sk_stream_wmem_schedule() -> sk_wmem_schedule() sk_charge_skb() -> sk_mem_charge() Removeing sk_stream_rfree(): consolidates into sock_rfree() sk_stream_set_owner_r(): consolidates into skb_set_owner_r() sk_stream_mem_schedule() The following functions are added. sk_has_account(): check if the protocol supports accounting sk_mem_uncharge(): do the opposite of sk_mem_charge() In addition, to achieve consolidation, updating sk_wmem_queued is removed from sk_mem_charge(). Next, to consolidate memory accounting functions, this patch adds memory accounting calls to network core functions. Moreover, present memory accounting call is renamed to new accounting call. Finally we replace present memory accounting calls with new interface in TCP and SCTP. Signed-off-by: Takahiro Yasui <tyasui@redhat.com> Signed-off-by: Hideo Aoki <haoki@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-31 08:11:19 +00:00
return 1;
} else if (refcount_read(&sk->sk_wmem_alloc) < wmem0) {
[NET] CORE: Introducing new memory accounting interface. This patch introduces new memory accounting functions for each network protocol. Most of them are renamed from memory accounting functions for stream protocols. At the same time, some stream memory accounting functions are removed since other functions do same thing. Renaming: sk_stream_free_skb() -> sk_wmem_free_skb() __sk_stream_mem_reclaim() -> __sk_mem_reclaim() sk_stream_mem_reclaim() -> sk_mem_reclaim() sk_stream_mem_schedule -> __sk_mem_schedule() sk_stream_pages() -> sk_mem_pages() sk_stream_rmem_schedule() -> sk_rmem_schedule() sk_stream_wmem_schedule() -> sk_wmem_schedule() sk_charge_skb() -> sk_mem_charge() Removeing sk_stream_rfree(): consolidates into sock_rfree() sk_stream_set_owner_r(): consolidates into skb_set_owner_r() sk_stream_mem_schedule() The following functions are added. sk_has_account(): check if the protocol supports accounting sk_mem_uncharge(): do the opposite of sk_mem_charge() In addition, to achieve consolidation, updating sk_wmem_queued is removed from sk_mem_charge(). Next, to consolidate memory accounting functions, this patch adds memory accounting calls to network core functions. Moreover, present memory accounting call is renamed to new accounting call. Finally we replace present memory accounting calls with new interface in TCP and SCTP. Signed-off-by: Takahiro Yasui <tyasui@redhat.com> Signed-off-by: Hideo Aoki <haoki@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-31 08:11:19 +00:00
return 1;
}
[NET] CORE: Introducing new memory accounting interface. This patch introduces new memory accounting functions for each network protocol. Most of them are renamed from memory accounting functions for stream protocols. At the same time, some stream memory accounting functions are removed since other functions do same thing. Renaming: sk_stream_free_skb() -> sk_wmem_free_skb() __sk_stream_mem_reclaim() -> __sk_mem_reclaim() sk_stream_mem_reclaim() -> sk_mem_reclaim() sk_stream_mem_schedule -> __sk_mem_schedule() sk_stream_pages() -> sk_mem_pages() sk_stream_rmem_schedule() -> sk_rmem_schedule() sk_stream_wmem_schedule() -> sk_wmem_schedule() sk_charge_skb() -> sk_mem_charge() Removeing sk_stream_rfree(): consolidates into sock_rfree() sk_stream_set_owner_r(): consolidates into skb_set_owner_r() sk_stream_mem_schedule() The following functions are added. sk_has_account(): check if the protocol supports accounting sk_mem_uncharge(): do the opposite of sk_mem_charge() In addition, to achieve consolidation, updating sk_wmem_queued is removed from sk_mem_charge(). Next, to consolidate memory accounting functions, this patch adds memory accounting calls to network core functions. Moreover, present memory accounting call is renamed to new accounting call. Finally we replace present memory accounting calls with new interface in TCP and SCTP. Signed-off-by: Takahiro Yasui <tyasui@redhat.com> Signed-off-by: Hideo Aoki <haoki@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-31 08:11:19 +00:00
}
if (sk_has_memory_pressure(sk)) {
u64 alloc;
if (!sk_under_memory_pressure(sk))
return 1;
alloc = sk_sockets_allocated_read_positive(sk);
if (sk_prot_mem_limits(sk, 2) > alloc *
[NET] CORE: Introducing new memory accounting interface. This patch introduces new memory accounting functions for each network protocol. Most of them are renamed from memory accounting functions for stream protocols. At the same time, some stream memory accounting functions are removed since other functions do same thing. Renaming: sk_stream_free_skb() -> sk_wmem_free_skb() __sk_stream_mem_reclaim() -> __sk_mem_reclaim() sk_stream_mem_reclaim() -> sk_mem_reclaim() sk_stream_mem_schedule -> __sk_mem_schedule() sk_stream_pages() -> sk_mem_pages() sk_stream_rmem_schedule() -> sk_rmem_schedule() sk_stream_wmem_schedule() -> sk_wmem_schedule() sk_charge_skb() -> sk_mem_charge() Removeing sk_stream_rfree(): consolidates into sock_rfree() sk_stream_set_owner_r(): consolidates into skb_set_owner_r() sk_stream_mem_schedule() The following functions are added. sk_has_account(): check if the protocol supports accounting sk_mem_uncharge(): do the opposite of sk_mem_charge() In addition, to achieve consolidation, updating sk_wmem_queued is removed from sk_mem_charge(). Next, to consolidate memory accounting functions, this patch adds memory accounting calls to network core functions. Moreover, present memory accounting call is renamed to new accounting call. Finally we replace present memory accounting calls with new interface in TCP and SCTP. Signed-off-by: Takahiro Yasui <tyasui@redhat.com> Signed-off-by: Hideo Aoki <haoki@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-31 08:11:19 +00:00
sk_mem_pages(sk->sk_wmem_queued +
atomic_read(&sk->sk_rmem_alloc) +
sk->sk_forward_alloc))
return 1;
}
suppress_allocation:
if (kind == SK_MEM_SEND && sk->sk_type == SOCK_STREAM) {
sk_stream_moderate_sndbuf(sk);
/* Fail only if socket is _under_ its sndbuf.
* In this case we cannot block, so that we have to fail.
*/
if (sk->sk_wmem_queued + size >= sk->sk_sndbuf)
return 1;
}
if (kind == SK_MEM_SEND || (kind == SK_MEM_RECV && charged))
trace_sock_exceed_buf_limit(sk, prot, allocated, kind);
sk_memory_allocated_sub(sk, amt);
if (mem_cgroup_sockets_enabled && sk->sk_memcg)
mem_cgroup_uncharge_skmem(sk->sk_memcg, amt);
net: tcp_memcontrol: sanitize tcp memory accounting callbacks There won't be a tcp control soft limit, so integrating the memcg code into the global skmem limiting scheme complicates things unnecessarily. Replace this with simple and clear charge and uncharge calls--hidden behind a jump label--to account skb memory. Note that this is not purely aesthetic: as a result of shoehorning the per-memcg code into the same memory accounting functions that handle the global level, the old code would compare the per-memcg consumption against the smaller of the per-memcg limit and the global limit. This allowed the total consumption of multiple sockets to exceed the global limit, as long as the individual sockets stayed within bounds. After this change, the code will always compare the per-memcg consumption to the per-memcg limit, and the global consumption to the global limit, and thus close this loophole. Without a soft limit, the per-memcg memory pressure state in sockets is generally questionable. However, we did it until now, so we continue to enter it when the hard limit is hit, and packets are dropped, to let other sockets in the cgroup know that they shouldn't grow their transmit windows, either. However, keep it simple in the new callback model and leave memory pressure lazily when the next packet is accepted (as opposed to doing it synchroneously when packets are processed). When packets are dropped, network performance will already be in the toilet, so that should be a reasonable trade-off. As described above, consumption is now checked on the per-memcg level and the global level separately. Likewise, memory pressure states are maintained on both the per-memcg level and the global level, and a socket is considered under pressure when either level asserts as much. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Vladimir Davydov <vdavydov@virtuozzo.com> Acked-by: David S. Miller <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-14 23:21:14 +00:00
[NET] CORE: Introducing new memory accounting interface. This patch introduces new memory accounting functions for each network protocol. Most of them are renamed from memory accounting functions for stream protocols. At the same time, some stream memory accounting functions are removed since other functions do same thing. Renaming: sk_stream_free_skb() -> sk_wmem_free_skb() __sk_stream_mem_reclaim() -> __sk_mem_reclaim() sk_stream_mem_reclaim() -> sk_mem_reclaim() sk_stream_mem_schedule -> __sk_mem_schedule() sk_stream_pages() -> sk_mem_pages() sk_stream_rmem_schedule() -> sk_rmem_schedule() sk_stream_wmem_schedule() -> sk_wmem_schedule() sk_charge_skb() -> sk_mem_charge() Removeing sk_stream_rfree(): consolidates into sock_rfree() sk_stream_set_owner_r(): consolidates into skb_set_owner_r() sk_stream_mem_schedule() The following functions are added. sk_has_account(): check if the protocol supports accounting sk_mem_uncharge(): do the opposite of sk_mem_charge() In addition, to achieve consolidation, updating sk_wmem_queued is removed from sk_mem_charge(). Next, to consolidate memory accounting functions, this patch adds memory accounting calls to network core functions. Moreover, present memory accounting call is renamed to new accounting call. Finally we replace present memory accounting calls with new interface in TCP and SCTP. Signed-off-by: Takahiro Yasui <tyasui@redhat.com> Signed-off-by: Hideo Aoki <haoki@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-31 08:11:19 +00:00
return 0;
}
EXPORT_SYMBOL(__sk_mem_raise_allocated);
/**
* __sk_mem_schedule - increase sk_forward_alloc and memory_allocated
* @sk: socket
* @size: memory size to allocate
* @kind: allocation type
*
* If kind is SK_MEM_SEND, it means wmem allocation. Otherwise it means
* rmem allocation. This function assumes that protocols which have
* memory_pressure use sk_wmem_queued as write buffer accounting.
*/
int __sk_mem_schedule(struct sock *sk, int size, int kind)
{
int ret, amt = sk_mem_pages(size);
sk->sk_forward_alloc += amt << SK_MEM_QUANTUM_SHIFT;
ret = __sk_mem_raise_allocated(sk, size, amt, kind);
if (!ret)
sk->sk_forward_alloc -= amt << SK_MEM_QUANTUM_SHIFT;
return ret;
}
[NET] CORE: Introducing new memory accounting interface. This patch introduces new memory accounting functions for each network protocol. Most of them are renamed from memory accounting functions for stream protocols. At the same time, some stream memory accounting functions are removed since other functions do same thing. Renaming: sk_stream_free_skb() -> sk_wmem_free_skb() __sk_stream_mem_reclaim() -> __sk_mem_reclaim() sk_stream_mem_reclaim() -> sk_mem_reclaim() sk_stream_mem_schedule -> __sk_mem_schedule() sk_stream_pages() -> sk_mem_pages() sk_stream_rmem_schedule() -> sk_rmem_schedule() sk_stream_wmem_schedule() -> sk_wmem_schedule() sk_charge_skb() -> sk_mem_charge() Removeing sk_stream_rfree(): consolidates into sock_rfree() sk_stream_set_owner_r(): consolidates into skb_set_owner_r() sk_stream_mem_schedule() The following functions are added. sk_has_account(): check if the protocol supports accounting sk_mem_uncharge(): do the opposite of sk_mem_charge() In addition, to achieve consolidation, updating sk_wmem_queued is removed from sk_mem_charge(). Next, to consolidate memory accounting functions, this patch adds memory accounting calls to network core functions. Moreover, present memory accounting call is renamed to new accounting call. Finally we replace present memory accounting calls with new interface in TCP and SCTP. Signed-off-by: Takahiro Yasui <tyasui@redhat.com> Signed-off-by: Hideo Aoki <haoki@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-31 08:11:19 +00:00
EXPORT_SYMBOL(__sk_mem_schedule);
/**
* __sk_mem_reduce_allocated - reclaim memory_allocated
[NET] CORE: Introducing new memory accounting interface. This patch introduces new memory accounting functions for each network protocol. Most of them are renamed from memory accounting functions for stream protocols. At the same time, some stream memory accounting functions are removed since other functions do same thing. Renaming: sk_stream_free_skb() -> sk_wmem_free_skb() __sk_stream_mem_reclaim() -> __sk_mem_reclaim() sk_stream_mem_reclaim() -> sk_mem_reclaim() sk_stream_mem_schedule -> __sk_mem_schedule() sk_stream_pages() -> sk_mem_pages() sk_stream_rmem_schedule() -> sk_rmem_schedule() sk_stream_wmem_schedule() -> sk_wmem_schedule() sk_charge_skb() -> sk_mem_charge() Removeing sk_stream_rfree(): consolidates into sock_rfree() sk_stream_set_owner_r(): consolidates into skb_set_owner_r() sk_stream_mem_schedule() The following functions are added. sk_has_account(): check if the protocol supports accounting sk_mem_uncharge(): do the opposite of sk_mem_charge() In addition, to achieve consolidation, updating sk_wmem_queued is removed from sk_mem_charge(). Next, to consolidate memory accounting functions, this patch adds memory accounting calls to network core functions. Moreover, present memory accounting call is renamed to new accounting call. Finally we replace present memory accounting calls with new interface in TCP and SCTP. Signed-off-by: Takahiro Yasui <tyasui@redhat.com> Signed-off-by: Hideo Aoki <haoki@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-31 08:11:19 +00:00
* @sk: socket
* @amount: number of quanta
*
* Similar to __sk_mem_reclaim(), but does not update sk_forward_alloc
[NET] CORE: Introducing new memory accounting interface. This patch introduces new memory accounting functions for each network protocol. Most of them are renamed from memory accounting functions for stream protocols. At the same time, some stream memory accounting functions are removed since other functions do same thing. Renaming: sk_stream_free_skb() -> sk_wmem_free_skb() __sk_stream_mem_reclaim() -> __sk_mem_reclaim() sk_stream_mem_reclaim() -> sk_mem_reclaim() sk_stream_mem_schedule -> __sk_mem_schedule() sk_stream_pages() -> sk_mem_pages() sk_stream_rmem_schedule() -> sk_rmem_schedule() sk_stream_wmem_schedule() -> sk_wmem_schedule() sk_charge_skb() -> sk_mem_charge() Removeing sk_stream_rfree(): consolidates into sock_rfree() sk_stream_set_owner_r(): consolidates into skb_set_owner_r() sk_stream_mem_schedule() The following functions are added. sk_has_account(): check if the protocol supports accounting sk_mem_uncharge(): do the opposite of sk_mem_charge() In addition, to achieve consolidation, updating sk_wmem_queued is removed from sk_mem_charge(). Next, to consolidate memory accounting functions, this patch adds memory accounting calls to network core functions. Moreover, present memory accounting call is renamed to new accounting call. Finally we replace present memory accounting calls with new interface in TCP and SCTP. Signed-off-by: Takahiro Yasui <tyasui@redhat.com> Signed-off-by: Hideo Aoki <haoki@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-31 08:11:19 +00:00
*/
void __sk_mem_reduce_allocated(struct sock *sk, int amount)
[NET] CORE: Introducing new memory accounting interface. This patch introduces new memory accounting functions for each network protocol. Most of them are renamed from memory accounting functions for stream protocols. At the same time, some stream memory accounting functions are removed since other functions do same thing. Renaming: sk_stream_free_skb() -> sk_wmem_free_skb() __sk_stream_mem_reclaim() -> __sk_mem_reclaim() sk_stream_mem_reclaim() -> sk_mem_reclaim() sk_stream_mem_schedule -> __sk_mem_schedule() sk_stream_pages() -> sk_mem_pages() sk_stream_rmem_schedule() -> sk_rmem_schedule() sk_stream_wmem_schedule() -> sk_wmem_schedule() sk_charge_skb() -> sk_mem_charge() Removeing sk_stream_rfree(): consolidates into sock_rfree() sk_stream_set_owner_r(): consolidates into skb_set_owner_r() sk_stream_mem_schedule() The following functions are added. sk_has_account(): check if the protocol supports accounting sk_mem_uncharge(): do the opposite of sk_mem_charge() In addition, to achieve consolidation, updating sk_wmem_queued is removed from sk_mem_charge(). Next, to consolidate memory accounting functions, this patch adds memory accounting calls to network core functions. Moreover, present memory accounting call is renamed to new accounting call. Finally we replace present memory accounting calls with new interface in TCP and SCTP. Signed-off-by: Takahiro Yasui <tyasui@redhat.com> Signed-off-by: Hideo Aoki <haoki@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-31 08:11:19 +00:00
{
sk_memory_allocated_sub(sk, amount);
[NET] CORE: Introducing new memory accounting interface. This patch introduces new memory accounting functions for each network protocol. Most of them are renamed from memory accounting functions for stream protocols. At the same time, some stream memory accounting functions are removed since other functions do same thing. Renaming: sk_stream_free_skb() -> sk_wmem_free_skb() __sk_stream_mem_reclaim() -> __sk_mem_reclaim() sk_stream_mem_reclaim() -> sk_mem_reclaim() sk_stream_mem_schedule -> __sk_mem_schedule() sk_stream_pages() -> sk_mem_pages() sk_stream_rmem_schedule() -> sk_rmem_schedule() sk_stream_wmem_schedule() -> sk_wmem_schedule() sk_charge_skb() -> sk_mem_charge() Removeing sk_stream_rfree(): consolidates into sock_rfree() sk_stream_set_owner_r(): consolidates into skb_set_owner_r() sk_stream_mem_schedule() The following functions are added. sk_has_account(): check if the protocol supports accounting sk_mem_uncharge(): do the opposite of sk_mem_charge() In addition, to achieve consolidation, updating sk_wmem_queued is removed from sk_mem_charge(). Next, to consolidate memory accounting functions, this patch adds memory accounting calls to network core functions. Moreover, present memory accounting call is renamed to new accounting call. Finally we replace present memory accounting calls with new interface in TCP and SCTP. Signed-off-by: Takahiro Yasui <tyasui@redhat.com> Signed-off-by: Hideo Aoki <haoki@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-31 08:11:19 +00:00
if (mem_cgroup_sockets_enabled && sk->sk_memcg)
mem_cgroup_uncharge_skmem(sk->sk_memcg, amount);
net: tcp_memcontrol: sanitize tcp memory accounting callbacks There won't be a tcp control soft limit, so integrating the memcg code into the global skmem limiting scheme complicates things unnecessarily. Replace this with simple and clear charge and uncharge calls--hidden behind a jump label--to account skb memory. Note that this is not purely aesthetic: as a result of shoehorning the per-memcg code into the same memory accounting functions that handle the global level, the old code would compare the per-memcg consumption against the smaller of the per-memcg limit and the global limit. This allowed the total consumption of multiple sockets to exceed the global limit, as long as the individual sockets stayed within bounds. After this change, the code will always compare the per-memcg consumption to the per-memcg limit, and the global consumption to the global limit, and thus close this loophole. Without a soft limit, the per-memcg memory pressure state in sockets is generally questionable. However, we did it until now, so we continue to enter it when the hard limit is hit, and packets are dropped, to let other sockets in the cgroup know that they shouldn't grow their transmit windows, either. However, keep it simple in the new callback model and leave memory pressure lazily when the next packet is accepted (as opposed to doing it synchroneously when packets are processed). When packets are dropped, network performance will already be in the toilet, so that should be a reasonable trade-off. As described above, consumption is now checked on the per-memcg level and the global level separately. Likewise, memory pressure states are maintained on both the per-memcg level and the global level, and a socket is considered under pressure when either level asserts as much. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Vladimir Davydov <vdavydov@virtuozzo.com> Acked-by: David S. Miller <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-01-14 23:21:14 +00:00
if (sk_under_memory_pressure(sk) &&
(sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)))
sk_leave_memory_pressure(sk);
[NET] CORE: Introducing new memory accounting interface. This patch introduces new memory accounting functions for each network protocol. Most of them are renamed from memory accounting functions for stream protocols. At the same time, some stream memory accounting functions are removed since other functions do same thing. Renaming: sk_stream_free_skb() -> sk_wmem_free_skb() __sk_stream_mem_reclaim() -> __sk_mem_reclaim() sk_stream_mem_reclaim() -> sk_mem_reclaim() sk_stream_mem_schedule -> __sk_mem_schedule() sk_stream_pages() -> sk_mem_pages() sk_stream_rmem_schedule() -> sk_rmem_schedule() sk_stream_wmem_schedule() -> sk_wmem_schedule() sk_charge_skb() -> sk_mem_charge() Removeing sk_stream_rfree(): consolidates into sock_rfree() sk_stream_set_owner_r(): consolidates into skb_set_owner_r() sk_stream_mem_schedule() The following functions are added. sk_has_account(): check if the protocol supports accounting sk_mem_uncharge(): do the opposite of sk_mem_charge() In addition, to achieve consolidation, updating sk_wmem_queued is removed from sk_mem_charge(). Next, to consolidate memory accounting functions, this patch adds memory accounting calls to network core functions. Moreover, present memory accounting call is renamed to new accounting call. Finally we replace present memory accounting calls with new interface in TCP and SCTP. Signed-off-by: Takahiro Yasui <tyasui@redhat.com> Signed-off-by: Hideo Aoki <haoki@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-31 08:11:19 +00:00
}
EXPORT_SYMBOL(__sk_mem_reduce_allocated);
/**
* __sk_mem_reclaim - reclaim sk_forward_alloc and memory_allocated
* @sk: socket
* @amount: number of bytes (rounded down to a SK_MEM_QUANTUM multiple)
*/
void __sk_mem_reclaim(struct sock *sk, int amount)
{
amount >>= SK_MEM_QUANTUM_SHIFT;
sk->sk_forward_alloc -= amount << SK_MEM_QUANTUM_SHIFT;
__sk_mem_reduce_allocated(sk, amount);
}
[NET] CORE: Introducing new memory accounting interface. This patch introduces new memory accounting functions for each network protocol. Most of them are renamed from memory accounting functions for stream protocols. At the same time, some stream memory accounting functions are removed since other functions do same thing. Renaming: sk_stream_free_skb() -> sk_wmem_free_skb() __sk_stream_mem_reclaim() -> __sk_mem_reclaim() sk_stream_mem_reclaim() -> sk_mem_reclaim() sk_stream_mem_schedule -> __sk_mem_schedule() sk_stream_pages() -> sk_mem_pages() sk_stream_rmem_schedule() -> sk_rmem_schedule() sk_stream_wmem_schedule() -> sk_wmem_schedule() sk_charge_skb() -> sk_mem_charge() Removeing sk_stream_rfree(): consolidates into sock_rfree() sk_stream_set_owner_r(): consolidates into skb_set_owner_r() sk_stream_mem_schedule() The following functions are added. sk_has_account(): check if the protocol supports accounting sk_mem_uncharge(): do the opposite of sk_mem_charge() In addition, to achieve consolidation, updating sk_wmem_queued is removed from sk_mem_charge(). Next, to consolidate memory accounting functions, this patch adds memory accounting calls to network core functions. Moreover, present memory accounting call is renamed to new accounting call. Finally we replace present memory accounting calls with new interface in TCP and SCTP. Signed-off-by: Takahiro Yasui <tyasui@redhat.com> Signed-off-by: Hideo Aoki <haoki@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-31 08:11:19 +00:00
EXPORT_SYMBOL(__sk_mem_reclaim);
int sk_set_peek_off(struct sock *sk, int val)
{
sk->sk_peek_off = val;
return 0;
}
EXPORT_SYMBOL_GPL(sk_set_peek_off);
[NET] CORE: Introducing new memory accounting interface. This patch introduces new memory accounting functions for each network protocol. Most of them are renamed from memory accounting functions for stream protocols. At the same time, some stream memory accounting functions are removed since other functions do same thing. Renaming: sk_stream_free_skb() -> sk_wmem_free_skb() __sk_stream_mem_reclaim() -> __sk_mem_reclaim() sk_stream_mem_reclaim() -> sk_mem_reclaim() sk_stream_mem_schedule -> __sk_mem_schedule() sk_stream_pages() -> sk_mem_pages() sk_stream_rmem_schedule() -> sk_rmem_schedule() sk_stream_wmem_schedule() -> sk_wmem_schedule() sk_charge_skb() -> sk_mem_charge() Removeing sk_stream_rfree(): consolidates into sock_rfree() sk_stream_set_owner_r(): consolidates into skb_set_owner_r() sk_stream_mem_schedule() The following functions are added. sk_has_account(): check if the protocol supports accounting sk_mem_uncharge(): do the opposite of sk_mem_charge() In addition, to achieve consolidation, updating sk_wmem_queued is removed from sk_mem_charge(). Next, to consolidate memory accounting functions, this patch adds memory accounting calls to network core functions. Moreover, present memory accounting call is renamed to new accounting call. Finally we replace present memory accounting calls with new interface in TCP and SCTP. Signed-off-by: Takahiro Yasui <tyasui@redhat.com> Signed-off-by: Hideo Aoki <haoki@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-31 08:11:19 +00:00
/*
* Set of default routines for initialising struct proto_ops when
* the protocol does not support a particular function. In certain
* cases where it makes no sense for a protocol to have a "do nothing"
* function, some default processing is provided.
*/
int sock_no_bind(struct socket *sock, struct sockaddr *saddr, int len)
{
return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_bind);
int sock_no_connect(struct socket *sock, struct sockaddr *saddr,
int len, int flags)
{
return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_connect);
int sock_no_socketpair(struct socket *sock1, struct socket *sock2)
{
return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_socketpair);
net: Work around lockdep limitation in sockets that use sockets Lockdep issues a circular dependency warning when AFS issues an operation through AF_RXRPC from a context in which the VFS/VM holds the mmap_sem. The theory lockdep comes up with is as follows: (1) If the pagefault handler decides it needs to read pages from AFS, it calls AFS with mmap_sem held and AFS begins an AF_RXRPC call, but creating a call requires the socket lock: mmap_sem must be taken before sk_lock-AF_RXRPC (2) afs_open_socket() opens an AF_RXRPC socket and binds it. rxrpc_bind() binds the underlying UDP socket whilst holding its socket lock. inet_bind() takes its own socket lock: sk_lock-AF_RXRPC must be taken before sk_lock-AF_INET (3) Reading from a TCP socket into a userspace buffer might cause a fault and thus cause the kernel to take the mmap_sem, but the TCP socket is locked whilst doing this: sk_lock-AF_INET must be taken before mmap_sem However, lockdep's theory is wrong in this instance because it deals only with lock classes and not individual locks. The AF_INET lock in (2) isn't really equivalent to the AF_INET lock in (3) as the former deals with a socket entirely internal to the kernel that never sees userspace. This is a limitation in the design of lockdep. Fix the general case by: (1) Double up all the locking keys used in sockets so that one set are used if the socket is created by userspace and the other set is used if the socket is created by the kernel. (2) Store the kern parameter passed to sk_alloc() in a variable in the sock struct (sk_kern_sock). This informs sock_lock_init(), sock_init_data() and sk_clone_lock() as to the lock keys to be used. Note that the child created by sk_clone_lock() inherits the parent's kern setting. (3) Add a 'kern' parameter to ->accept() that is analogous to the one passed in to ->create() that distinguishes whether kernel_accept() or sys_accept4() was the caller and can be passed to sk_alloc(). Note that a lot of accept functions merely dequeue an already allocated socket. I haven't touched these as the new socket already exists before we get the parameter. Note also that there are a couple of places where I've made the accepted socket unconditionally kernel-based: irda_accept() rds_rcp_accept_one() tcp_accept_from_sock() because they follow a sock_create_kern() and accept off of that. Whilst creating this, I noticed that lustre and ocfs don't create sockets through sock_create_kern() and thus they aren't marked as for-kernel, though they appear to be internal. I wonder if these should do that so that they use the new set of lock keys. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-09 08:09:05 +00:00
int sock_no_accept(struct socket *sock, struct socket *newsock, int flags,
bool kern)
{
return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_accept);
int sock_no_getname(struct socket *sock, struct sockaddr *saddr,
net: make getname() functions return length rather than use int* parameter Changes since v1: Added changes in these files: drivers/infiniband/hw/usnic/usnic_transport.c drivers/staging/lustre/lnet/lnet/lib-socket.c drivers/target/iscsi/iscsi_target_login.c drivers/vhost/net.c fs/dlm/lowcomms.c fs/ocfs2/cluster/tcp.c security/tomoyo/network.c Before: All these functions either return a negative error indicator, or store length of sockaddr into "int *socklen" parameter and return zero on success. "int *socklen" parameter is awkward. For example, if caller does not care, it still needs to provide on-stack storage for the value it does not need. None of the many FOO_getname() functions of various protocols ever used old value of *socklen. They always just overwrite it. This change drops this parameter, and makes all these functions, on success, return length of sockaddr. It's always >= 0 and can be differentiated from an error. Tests in callers are changed from "if (err)" to "if (err < 0)", where needed. rpc_sockname() lost "int buflen" parameter, since its only use was to be passed to kernel_getsockname() as &buflen and subsequently not used in any way. Userspace API is not changed. text data bss dec hex filename 30108430 2633624 873672 33615726 200ef6e vmlinux.before.o 30108109 2633612 873672 33615393 200ee21 vmlinux.o Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com> CC: David S. Miller <davem@davemloft.net> CC: linux-kernel@vger.kernel.org CC: netdev@vger.kernel.org CC: linux-bluetooth@vger.kernel.org CC: linux-decnet-user@lists.sourceforge.net CC: linux-wireless@vger.kernel.org CC: linux-rdma@vger.kernel.org CC: linux-sctp@vger.kernel.org CC: linux-nfs@vger.kernel.org CC: linux-x25@vger.kernel.org Signed-off-by: David S. Miller <davem@davemloft.net>
2018-02-12 19:00:20 +00:00
int peer)
{
return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_getname);
int sock_no_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
{
return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_ioctl);
int sock_no_listen(struct socket *sock, int backlog)
{
return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_listen);
int sock_no_shutdown(struct socket *sock, int how)
{
return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_shutdown);
int sock_no_sendmsg(struct socket *sock, struct msghdr *m, size_t len)
{
return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_sendmsg);
int sock_no_sendmsg_locked(struct sock *sk, struct msghdr *m, size_t len)
{
return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_sendmsg_locked);
int sock_no_recvmsg(struct socket *sock, struct msghdr *m, size_t len,
int flags)
{
return -EOPNOTSUPP;
}
EXPORT_SYMBOL(sock_no_recvmsg);
int sock_no_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma)
{
/* Mirror missing mmap method error code */
return -ENODEV;
}
EXPORT_SYMBOL(sock_no_mmap);
/*
* When a file is received (via SCM_RIGHTS, etc), we must bump the
* various sock-based usage counts.
*/
void __receive_sock(struct file *file)
{
struct socket *sock;
sock = sock_from_file(file);
if (sock) {
sock_update_netprioidx(&sock->sk->sk_cgrp_data);
sock_update_classid(&sock->sk->sk_cgrp_data);
}
}
ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags)
{
ssize_t res;
struct msghdr msg = {.msg_flags = flags};
struct kvec iov;
char *kaddr = kmap(page);
iov.iov_base = kaddr + offset;
iov.iov_len = size;
res = kernel_sendmsg(sock, &msg, &iov, 1, size);
kunmap(page);
return res;
}
EXPORT_SYMBOL(sock_no_sendpage);
ssize_t sock_no_sendpage_locked(struct sock *sk, struct page *page,
int offset, size_t size, int flags)
{
ssize_t res;
struct msghdr msg = {.msg_flags = flags};
struct kvec iov;
char *kaddr = kmap(page);
iov.iov_base = kaddr + offset;
iov.iov_len = size;
res = kernel_sendmsg_locked(sk, &msg, &iov, 1, size);
kunmap(page);
return res;
}
EXPORT_SYMBOL(sock_no_sendpage_locked);
/*
* Default Socket Callbacks
*/
static void sock_def_wakeup(struct sock *sk)
{
net: sock_def_readable() and friends RCU conversion sk_callback_lock rwlock actually protects sk->sk_sleep pointer, so we need two atomic operations (and associated dirtying) per incoming packet. RCU conversion is pretty much needed : 1) Add a new structure, called "struct socket_wq" to hold all fields that will need rcu_read_lock() protection (currently: a wait_queue_head_t and a struct fasync_struct pointer). [Future patch will add a list anchor for wakeup coalescing] 2) Attach one of such structure to each "struct socket" created in sock_alloc_inode(). 3) Respect RCU grace period when freeing a "struct socket_wq" 4) Change sk_sleep pointer in "struct sock" by sk_wq, pointer to "struct socket_wq" 5) Change sk_sleep() function to use new sk->sk_wq instead of sk->sk_sleep 6) Change sk_has_sleeper() to wq_has_sleeper() that must be used inside a rcu_read_lock() section. 7) Change all sk_has_sleeper() callers to : - Use rcu_read_lock() instead of read_lock(&sk->sk_callback_lock) - Use wq_has_sleeper() to eventually wakeup tasks. - Use rcu_read_unlock() instead of read_unlock(&sk->sk_callback_lock) 8) sock_wake_async() is modified to use rcu protection as well. 9) Exceptions : macvtap, drivers/net/tun.c, af_unix use integrated "struct socket_wq" instead of dynamically allocated ones. They dont need rcu freeing. Some cleanups or followups are probably needed, (possible sk_callback_lock conversion to a spinlock for example...). Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-29 11:01:49 +00:00
struct socket_wq *wq;
rcu_read_lock();
wq = rcu_dereference(sk->sk_wq);
if (skwq_has_sleeper(wq))
net: sock_def_readable() and friends RCU conversion sk_callback_lock rwlock actually protects sk->sk_sleep pointer, so we need two atomic operations (and associated dirtying) per incoming packet. RCU conversion is pretty much needed : 1) Add a new structure, called "struct socket_wq" to hold all fields that will need rcu_read_lock() protection (currently: a wait_queue_head_t and a struct fasync_struct pointer). [Future patch will add a list anchor for wakeup coalescing] 2) Attach one of such structure to each "struct socket" created in sock_alloc_inode(). 3) Respect RCU grace period when freeing a "struct socket_wq" 4) Change sk_sleep pointer in "struct sock" by sk_wq, pointer to "struct socket_wq" 5) Change sk_sleep() function to use new sk->sk_wq instead of sk->sk_sleep 6) Change sk_has_sleeper() to wq_has_sleeper() that must be used inside a rcu_read_lock() section. 7) Change all sk_has_sleeper() callers to : - Use rcu_read_lock() instead of read_lock(&sk->sk_callback_lock) - Use wq_has_sleeper() to eventually wakeup tasks. - Use rcu_read_unlock() instead of read_unlock(&sk->sk_callback_lock) 8) sock_wake_async() is modified to use rcu protection as well. 9) Exceptions : macvtap, drivers/net/tun.c, af_unix use integrated "struct socket_wq" instead of dynamically allocated ones. They dont need rcu freeing. Some cleanups or followups are probably needed, (possible sk_callback_lock conversion to a spinlock for example...). Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-29 11:01:49 +00:00
wake_up_interruptible_all(&wq->wait);
rcu_read_unlock();
}
static void sock_def_error_report(struct sock *sk)
{
net: sock_def_readable() and friends RCU conversion sk_callback_lock rwlock actually protects sk->sk_sleep pointer, so we need two atomic operations (and associated dirtying) per incoming packet. RCU conversion is pretty much needed : 1) Add a new structure, called "struct socket_wq" to hold all fields that will need rcu_read_lock() protection (currently: a wait_queue_head_t and a struct fasync_struct pointer). [Future patch will add a list anchor for wakeup coalescing] 2) Attach one of such structure to each "struct socket" created in sock_alloc_inode(). 3) Respect RCU grace period when freeing a "struct socket_wq" 4) Change sk_sleep pointer in "struct sock" by sk_wq, pointer to "struct socket_wq" 5) Change sk_sleep() function to use new sk->sk_wq instead of sk->sk_sleep 6) Change sk_has_sleeper() to wq_has_sleeper() that must be used inside a rcu_read_lock() section. 7) Change all sk_has_sleeper() callers to : - Use rcu_read_lock() instead of read_lock(&sk->sk_callback_lock) - Use wq_has_sleeper() to eventually wakeup tasks. - Use rcu_read_unlock() instead of read_unlock(&sk->sk_callback_lock) 8) sock_wake_async() is modified to use rcu protection as well. 9) Exceptions : macvtap, drivers/net/tun.c, af_unix use integrated "struct socket_wq" instead of dynamically allocated ones. They dont need rcu freeing. Some cleanups or followups are probably needed, (possible sk_callback_lock conversion to a spinlock for example...). Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-29 11:01:49 +00:00
struct socket_wq *wq;
rcu_read_lock();
wq = rcu_dereference(sk->sk_wq);
if (skwq_has_sleeper(wq))
wake_up_interruptible_poll(&wq->wait, EPOLLERR);
sk_wake_async(sk, SOCK_WAKE_IO, POLL_ERR);
net: sock_def_readable() and friends RCU conversion sk_callback_lock rwlock actually protects sk->sk_sleep pointer, so we need two atomic operations (and associated dirtying) per incoming packet. RCU conversion is pretty much needed : 1) Add a new structure, called "struct socket_wq" to hold all fields that will need rcu_read_lock() protection (currently: a wait_queue_head_t and a struct fasync_struct pointer). [Future patch will add a list anchor for wakeup coalescing] 2) Attach one of such structure to each "struct socket" created in sock_alloc_inode(). 3) Respect RCU grace period when freeing a "struct socket_wq" 4) Change sk_sleep pointer in "struct sock" by sk_wq, pointer to "struct socket_wq" 5) Change sk_sleep() function to use new sk->sk_wq instead of sk->sk_sleep 6) Change sk_has_sleeper() to wq_has_sleeper() that must be used inside a rcu_read_lock() section. 7) Change all sk_has_sleeper() callers to : - Use rcu_read_lock() instead of read_lock(&sk->sk_callback_lock) - Use wq_has_sleeper() to eventually wakeup tasks. - Use rcu_read_unlock() instead of read_unlock(&sk->sk_callback_lock) 8) sock_wake_async() is modified to use rcu protection as well. 9) Exceptions : macvtap, drivers/net/tun.c, af_unix use integrated "struct socket_wq" instead of dynamically allocated ones. They dont need rcu freeing. Some cleanups or followups are probably needed, (possible sk_callback_lock conversion to a spinlock for example...). Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-29 11:01:49 +00:00
rcu_read_unlock();
}
void sock_def_readable(struct sock *sk)
{
net: sock_def_readable() and friends RCU conversion sk_callback_lock rwlock actually protects sk->sk_sleep pointer, so we need two atomic operations (and associated dirtying) per incoming packet. RCU conversion is pretty much needed : 1) Add a new structure, called "struct socket_wq" to hold all fields that will need rcu_read_lock() protection (currently: a wait_queue_head_t and a struct fasync_struct pointer). [Future patch will add a list anchor for wakeup coalescing] 2) Attach one of such structure to each "struct socket" created in sock_alloc_inode(). 3) Respect RCU grace period when freeing a "struct socket_wq" 4) Change sk_sleep pointer in "struct sock" by sk_wq, pointer to "struct socket_wq" 5) Change sk_sleep() function to use new sk->sk_wq instead of sk->sk_sleep 6) Change sk_has_sleeper() to wq_has_sleeper() that must be used inside a rcu_read_lock() section. 7) Change all sk_has_sleeper() callers to : - Use rcu_read_lock() instead of read_lock(&sk->sk_callback_lock) - Use wq_has_sleeper() to eventually wakeup tasks. - Use rcu_read_unlock() instead of read_unlock(&sk->sk_callback_lock) 8) sock_wake_async() is modified to use rcu protection as well. 9) Exceptions : macvtap, drivers/net/tun.c, af_unix use integrated "struct socket_wq" instead of dynamically allocated ones. They dont need rcu freeing. Some cleanups or followups are probably needed, (possible sk_callback_lock conversion to a spinlock for example...). Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-29 11:01:49 +00:00
struct socket_wq *wq;
rcu_read_lock();
wq = rcu_dereference(sk->sk_wq);
if (skwq_has_sleeper(wq))
wake_up_interruptible_sync_poll(&wq->wait, EPOLLIN | EPOLLPRI |
EPOLLRDNORM | EPOLLRDBAND);
sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
net: sock_def_readable() and friends RCU conversion sk_callback_lock rwlock actually protects sk->sk_sleep pointer, so we need two atomic operations (and associated dirtying) per incoming packet. RCU conversion is pretty much needed : 1) Add a new structure, called "struct socket_wq" to hold all fields that will need rcu_read_lock() protection (currently: a wait_queue_head_t and a struct fasync_struct pointer). [Future patch will add a list anchor for wakeup coalescing] 2) Attach one of such structure to each "struct socket" created in sock_alloc_inode(). 3) Respect RCU grace period when freeing a "struct socket_wq" 4) Change sk_sleep pointer in "struct sock" by sk_wq, pointer to "struct socket_wq" 5) Change sk_sleep() function to use new sk->sk_wq instead of sk->sk_sleep 6) Change sk_has_sleeper() to wq_has_sleeper() that must be used inside a rcu_read_lock() section. 7) Change all sk_has_sleeper() callers to : - Use rcu_read_lock() instead of read_lock(&sk->sk_callback_lock) - Use wq_has_sleeper() to eventually wakeup tasks. - Use rcu_read_unlock() instead of read_unlock(&sk->sk_callback_lock) 8) sock_wake_async() is modified to use rcu protection as well. 9) Exceptions : macvtap, drivers/net/tun.c, af_unix use integrated "struct socket_wq" instead of dynamically allocated ones. They dont need rcu freeing. Some cleanups or followups are probably needed, (possible sk_callback_lock conversion to a spinlock for example...). Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-29 11:01:49 +00:00
rcu_read_unlock();
}
static void sock_def_write_space(struct sock *sk)
{
net: sock_def_readable() and friends RCU conversion sk_callback_lock rwlock actually protects sk->sk_sleep pointer, so we need two atomic operations (and associated dirtying) per incoming packet. RCU conversion is pretty much needed : 1) Add a new structure, called "struct socket_wq" to hold all fields that will need rcu_read_lock() protection (currently: a wait_queue_head_t and a struct fasync_struct pointer). [Future patch will add a list anchor for wakeup coalescing] 2) Attach one of such structure to each "struct socket" created in sock_alloc_inode(). 3) Respect RCU grace period when freeing a "struct socket_wq" 4) Change sk_sleep pointer in "struct sock" by sk_wq, pointer to "struct socket_wq" 5) Change sk_sleep() function to use new sk->sk_wq instead of sk->sk_sleep 6) Change sk_has_sleeper() to wq_has_sleeper() that must be used inside a rcu_read_lock() section. 7) Change all sk_has_sleeper() callers to : - Use rcu_read_lock() instead of read_lock(&sk->sk_callback_lock) - Use wq_has_sleeper() to eventually wakeup tasks. - Use rcu_read_unlock() instead of read_unlock(&sk->sk_callback_lock) 8) sock_wake_async() is modified to use rcu protection as well. 9) Exceptions : macvtap, drivers/net/tun.c, af_unix use integrated "struct socket_wq" instead of dynamically allocated ones. They dont need rcu freeing. Some cleanups or followups are probably needed, (possible sk_callback_lock conversion to a spinlock for example...). Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-29 11:01:49 +00:00
struct socket_wq *wq;
rcu_read_lock();
/* Do not wake up a writer until he can make "significant"
* progress. --DaveM
*/
if ((refcount_read(&sk->sk_wmem_alloc) << 1) <= READ_ONCE(sk->sk_sndbuf)) {
net: sock_def_readable() and friends RCU conversion sk_callback_lock rwlock actually protects sk->sk_sleep pointer, so we need two atomic operations (and associated dirtying) per incoming packet. RCU conversion is pretty much needed : 1) Add a new structure, called "struct socket_wq" to hold all fields that will need rcu_read_lock() protection (currently: a wait_queue_head_t and a struct fasync_struct pointer). [Future patch will add a list anchor for wakeup coalescing] 2) Attach one of such structure to each "struct socket" created in sock_alloc_inode(). 3) Respect RCU grace period when freeing a "struct socket_wq" 4) Change sk_sleep pointer in "struct sock" by sk_wq, pointer to "struct socket_wq" 5) Change sk_sleep() function to use new sk->sk_wq instead of sk->sk_sleep 6) Change sk_has_sleeper() to wq_has_sleeper() that must be used inside a rcu_read_lock() section. 7) Change all sk_has_sleeper() callers to : - Use rcu_read_lock() instead of read_lock(&sk->sk_callback_lock) - Use wq_has_sleeper() to eventually wakeup tasks. - Use rcu_read_unlock() instead of read_unlock(&sk->sk_callback_lock) 8) sock_wake_async() is modified to use rcu protection as well. 9) Exceptions : macvtap, drivers/net/tun.c, af_unix use integrated "struct socket_wq" instead of dynamically allocated ones. They dont need rcu freeing. Some cleanups or followups are probably needed, (possible sk_callback_lock conversion to a spinlock for example...). Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-29 11:01:49 +00:00
wq = rcu_dereference(sk->sk_wq);
if (skwq_has_sleeper(wq))
wake_up_interruptible_sync_poll(&wq->wait, EPOLLOUT |
EPOLLWRNORM | EPOLLWRBAND);
/* Should agree with poll, otherwise some programs break */
if (sock_writeable(sk))
sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT);
}
net: sock_def_readable() and friends RCU conversion sk_callback_lock rwlock actually protects sk->sk_sleep pointer, so we need two atomic operations (and associated dirtying) per incoming packet. RCU conversion is pretty much needed : 1) Add a new structure, called "struct socket_wq" to hold all fields that will need rcu_read_lock() protection (currently: a wait_queue_head_t and a struct fasync_struct pointer). [Future patch will add a list anchor for wakeup coalescing] 2) Attach one of such structure to each "struct socket" created in sock_alloc_inode(). 3) Respect RCU grace period when freeing a "struct socket_wq" 4) Change sk_sleep pointer in "struct sock" by sk_wq, pointer to "struct socket_wq" 5) Change sk_sleep() function to use new sk->sk_wq instead of sk->sk_sleep 6) Change sk_has_sleeper() to wq_has_sleeper() that must be used inside a rcu_read_lock() section. 7) Change all sk_has_sleeper() callers to : - Use rcu_read_lock() instead of read_lock(&sk->sk_callback_lock) - Use wq_has_sleeper() to eventually wakeup tasks. - Use rcu_read_unlock() instead of read_unlock(&sk->sk_callback_lock) 8) sock_wake_async() is modified to use rcu protection as well. 9) Exceptions : macvtap, drivers/net/tun.c, af_unix use integrated "struct socket_wq" instead of dynamically allocated ones. They dont need rcu freeing. Some cleanups or followups are probably needed, (possible sk_callback_lock conversion to a spinlock for example...). Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-29 11:01:49 +00:00
rcu_read_unlock();
}
static void sock_def_destruct(struct sock *sk)
{
}
void sk_send_sigurg(struct sock *sk)
{
if (sk->sk_socket && sk->sk_socket->file)
if (send_sigurg(&sk->sk_socket->file->f_owner))
sk_wake_async(sk, SOCK_WAKE_URG, POLL_PRI);
}
EXPORT_SYMBOL(sk_send_sigurg);
void sk_reset_timer(struct sock *sk, struct timer_list* timer,
unsigned long expires)
{
if (!mod_timer(timer, expires))
sock_hold(sk);
}
EXPORT_SYMBOL(sk_reset_timer);
void sk_stop_timer(struct sock *sk, struct timer_list* timer)
{
if (del_timer(timer))
__sock_put(sk);
}
EXPORT_SYMBOL(sk_stop_timer);
void sk_stop_timer_sync(struct sock *sk, struct timer_list *timer)
{
if (del_timer_sync(timer))
__sock_put(sk);
}
EXPORT_SYMBOL(sk_stop_timer_sync);
void sock_init_data(struct socket *sock, struct sock *sk)
{
sk_init_common(sk);
sk->sk_send_head = NULL;
timer_setup(&sk->sk_timer, NULL, 0);
sk->sk_allocation = GFP_KERNEL;
sk->sk_rcvbuf = sysctl_rmem_default;
sk->sk_sndbuf = sysctl_wmem_default;
sk->sk_state = TCP_CLOSE;
sk_set_socket(sk, sock);
sock_set_flag(sk, SOCK_ZAPPED);
if (sock) {
sk->sk_type = sock->type;
RCU_INIT_POINTER(sk->sk_wq, &sock->wq);
sock->sk = sk;
net: core: Add a UID field to struct sock. Protocol sockets (struct sock) don't have UIDs, but most of the time, they map 1:1 to userspace sockets (struct socket) which do. Various operations such as the iptables xt_owner match need access to the "UID of a socket", and do so by following the backpointer to the struct socket. This involves taking sk_callback_lock and doesn't work when there is no socket because userspace has already called close(). Simplify this by adding a sk_uid field to struct sock whose value matches the UID of the corresponding struct socket. The semantics are as follows: 1. Whenever sk_socket is non-null: sk_uid is the same as the UID in sk_socket, i.e., matches the return value of sock_i_uid. Specifically, the UID is set when userspace calls socket(), fchown(), or accept(). 2. When sk_socket is NULL, sk_uid is defined as follows: - For a socket that no longer has a sk_socket because userspace has called close(): the previous UID. - For a cloned socket (e.g., an incoming connection that is established but on which userspace has not yet called accept): the UID of the socket it was cloned from. - For a socket that has never had an sk_socket: UID 0 inside the user namespace corresponding to the network namespace the socket belongs to. Kernel sockets created by sock_create_kern are a special case of #1 and sk_uid is the user that created them. For kernel sockets created at network namespace creation time, such as the per-processor ICMP and TCP sockets, this is the user that created the network namespace. Signed-off-by: Lorenzo Colitti <lorenzo@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-03 17:23:41 +00:00
sk->sk_uid = SOCK_INODE(sock)->i_uid;
} else {
RCU_INIT_POINTER(sk->sk_wq, NULL);
net: core: Add a UID field to struct sock. Protocol sockets (struct sock) don't have UIDs, but most of the time, they map 1:1 to userspace sockets (struct socket) which do. Various operations such as the iptables xt_owner match need access to the "UID of a socket", and do so by following the backpointer to the struct socket. This involves taking sk_callback_lock and doesn't work when there is no socket because userspace has already called close(). Simplify this by adding a sk_uid field to struct sock whose value matches the UID of the corresponding struct socket. The semantics are as follows: 1. Whenever sk_socket is non-null: sk_uid is the same as the UID in sk_socket, i.e., matches the return value of sock_i_uid. Specifically, the UID is set when userspace calls socket(), fchown(), or accept(). 2. When sk_socket is NULL, sk_uid is defined as follows: - For a socket that no longer has a sk_socket because userspace has called close(): the previous UID. - For a cloned socket (e.g., an incoming connection that is established but on which userspace has not yet called accept): the UID of the socket it was cloned from. - For a socket that has never had an sk_socket: UID 0 inside the user namespace corresponding to the network namespace the socket belongs to. Kernel sockets created by sock_create_kern are a special case of #1 and sk_uid is the user that created them. For kernel sockets created at network namespace creation time, such as the per-processor ICMP and TCP sockets, this is the user that created the network namespace. Signed-off-by: Lorenzo Colitti <lorenzo@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-03 17:23:41 +00:00
sk->sk_uid = make_kuid(sock_net(sk)->user_ns, 0);
}
rwlock_init(&sk->sk_callback_lock);
net: Work around lockdep limitation in sockets that use sockets Lockdep issues a circular dependency warning when AFS issues an operation through AF_RXRPC from a context in which the VFS/VM holds the mmap_sem. The theory lockdep comes up with is as follows: (1) If the pagefault handler decides it needs to read pages from AFS, it calls AFS with mmap_sem held and AFS begins an AF_RXRPC call, but creating a call requires the socket lock: mmap_sem must be taken before sk_lock-AF_RXRPC (2) afs_open_socket() opens an AF_RXRPC socket and binds it. rxrpc_bind() binds the underlying UDP socket whilst holding its socket lock. inet_bind() takes its own socket lock: sk_lock-AF_RXRPC must be taken before sk_lock-AF_INET (3) Reading from a TCP socket into a userspace buffer might cause a fault and thus cause the kernel to take the mmap_sem, but the TCP socket is locked whilst doing this: sk_lock-AF_INET must be taken before mmap_sem However, lockdep's theory is wrong in this instance because it deals only with lock classes and not individual locks. The AF_INET lock in (2) isn't really equivalent to the AF_INET lock in (3) as the former deals with a socket entirely internal to the kernel that never sees userspace. This is a limitation in the design of lockdep. Fix the general case by: (1) Double up all the locking keys used in sockets so that one set are used if the socket is created by userspace and the other set is used if the socket is created by the kernel. (2) Store the kern parameter passed to sk_alloc() in a variable in the sock struct (sk_kern_sock). This informs sock_lock_init(), sock_init_data() and sk_clone_lock() as to the lock keys to be used. Note that the child created by sk_clone_lock() inherits the parent's kern setting. (3) Add a 'kern' parameter to ->accept() that is analogous to the one passed in to ->create() that distinguishes whether kernel_accept() or sys_accept4() was the caller and can be passed to sk_alloc(). Note that a lot of accept functions merely dequeue an already allocated socket. I haven't touched these as the new socket already exists before we get the parameter. Note also that there are a couple of places where I've made the accepted socket unconditionally kernel-based: irda_accept() rds_rcp_accept_one() tcp_accept_from_sock() because they follow a sock_create_kern() and accept off of that. Whilst creating this, I noticed that lustre and ocfs don't create sockets through sock_create_kern() and thus they aren't marked as for-kernel, though they appear to be internal. I wonder if these should do that so that they use the new set of lock keys. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-09 08:09:05 +00:00
if (sk->sk_kern_sock)
lockdep_set_class_and_name(
&sk->sk_callback_lock,
af_kern_callback_keys + sk->sk_family,
af_family_kern_clock_key_strings[sk->sk_family]);
else
lockdep_set_class_and_name(
&sk->sk_callback_lock,
af_callback_keys + sk->sk_family,
af_family_clock_key_strings[sk->sk_family]);
sk->sk_state_change = sock_def_wakeup;
sk->sk_data_ready = sock_def_readable;
sk->sk_write_space = sock_def_write_space;
sk->sk_error_report = sock_def_error_report;
sk->sk_destruct = sock_def_destruct;
net: use a per task frag allocator We currently use a per socket order-0 page cache for tcp_sendmsg() operations. This page is used to build fragments for skbs. Its done to increase probability of coalescing small write() into single segments in skbs still in write queue (not yet sent) But it wastes a lot of memory for applications handling many mostly idle sockets, since each socket holds one page in sk->sk_sndmsg_page Its also quite inefficient to build TSO 64KB packets, because we need about 16 pages per skb on arches where PAGE_SIZE = 4096, so we hit page allocator more than wanted. This patch adds a per task frag allocator and uses bigger pages, if available. An automatic fallback is done in case of memory pressure. (up to 32768 bytes per frag, thats order-3 pages on x86) This increases TCP stream performance by 20% on loopback device, but also benefits on other network devices, since 8x less frags are mapped on transmit and unmapped on tx completion. Alexander Duyck mentioned a probable performance win on systems with IOMMU enabled. Its possible some SG enabled hardware cant cope with bigger fragments, but their ndo_start_xmit() should already handle this, splitting a fragment in sub fragments, since some arches have PAGE_SIZE=65536 Successfully tested on various ethernet devices. (ixgbe, igb, bnx2x, tg3, mellanox mlx4) Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Ben Hutchings <bhutchings@solarflare.com> Cc: Vijay Subramanian <subramanian.vijay@gmail.com> Cc: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Vijay Subramanian <subramanian.vijay@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-23 23:04:42 +00:00
sk->sk_frag.page = NULL;
sk->sk_frag.offset = 0;
sk->sk_peek_off = -1;
sk->sk_peer_pid = NULL;
sk->sk_peer_cred = NULL;
sk->sk_write_pending = 0;
sk->sk_rcvlowat = 1;
sk->sk_rcvtimeo = MAX_SCHEDULE_TIMEOUT;
sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT;
sk->sk_stamp = SK_DEFAULT_STAMP;
#if BITS_PER_LONG==32
seqlock_init(&sk->sk_stamp_seq);
#endif
atomic_set(&sk->sk_zckey, 0);
#ifdef CONFIG_NET_RX_BUSY_POLL
sk->sk_napi_id = 0;
sk->sk_ll_usec = sysctl_net_busy_read;
#endif
sk->sk_max_pacing_rate = ~0UL;
sk->sk_pacing_rate = ~0UL;
WRITE_ONCE(sk->sk_pacing_shift, 10);
sk->sk_incoming_cpu = -1;
sk_rx_queue_clear(sk);
/*
* Before updating sk_refcnt, we must commit prior changes to memory
* (Documentation/RCU/rculist_nulls.rst for details)
*/
smp_wmb();
refcount_set(&sk->sk_refcnt, 1);
atomic_set(&sk->sk_drops, 0);
}
EXPORT_SYMBOL(sock_init_data);
void lock_sock_nested(struct sock *sk, int subclass)
{
might_sleep();
spin_lock_bh(&sk->sk_lock.slock);
if (sk->sk_lock.owned)
__lock_sock(sk);
sk->sk_lock.owned = 1;
spin_unlock(&sk->sk_lock.slock);
/*
* The sk_lock has mutex_lock() semantics here:
*/
mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_);
local_bh_enable();
}
EXPORT_SYMBOL(lock_sock_nested);
void release_sock(struct sock *sk)
{
spin_lock_bh(&sk->sk_lock.slock);
if (sk->sk_backlog.tail)
__release_sock(sk);
tcp: TCP Small Queues This introduce TSQ (TCP Small Queues) TSQ goal is to reduce number of TCP packets in xmit queues (qdisc & device queues), to reduce RTT and cwnd bias, part of the bufferbloat problem. sk->sk_wmem_alloc not allowed to grow above a given limit, allowing no more than ~128KB [1] per tcp socket in qdisc/dev layers at a given time. TSO packets are sized/capped to half the limit, so that we have two TSO packets in flight, allowing better bandwidth use. As a side effect, setting the limit to 40000 automatically reduces the standard gso max limit (65536) to 40000/2 : It can help to reduce latencies of high prio packets, having smaller TSO packets. This means we divert sock_wfree() to a tcp_wfree() handler, to queue/send following frames when skb_orphan() [2] is called for the already queued skbs. Results on my dev machines (tg3/ixgbe nics) are really impressive, using standard pfifo_fast, and with or without TSO/GSO. Without reduction of nominal bandwidth, we have reduction of buffering per bulk sender : < 1ms on Gbit (instead of 50ms with TSO) < 8ms on 100Mbit (instead of 132 ms) I no longer have 4 MBytes backlogged in qdisc by a single netperf session, and both side socket autotuning no longer use 4 Mbytes. As skb destructor cannot restart xmit itself ( as qdisc lock might be taken at this point ), we delegate the work to a tasklet. We use one tasklest per cpu for performance reasons. If tasklet finds a socket owned by the user, it sets TSQ_OWNED flag. This flag is tested in a new protocol method called from release_sock(), to eventually send new segments. [1] New /proc/sys/net/ipv4/tcp_limit_output_bytes tunable [2] skb_orphan() is usually called at TX completion time, but some drivers call it in their start_xmit() handler. These drivers should at least use BQL, or else a single TCP session can still fill the whole NIC TX ring, since TSQ will have no effect. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Dave Taht <dave.taht@bufferbloat.net> Cc: Tom Herbert <therbert@google.com> Cc: Matt Mathis <mattmathis@google.com> Cc: Yuchung Cheng <ycheng@google.com> Cc: Nandita Dukkipati <nanditad@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-07-11 05:50:31 +00:00
tcp: tcp_release_cb() should release socket ownership Lars Persson reported following deadlock : -000 |M:0x0:0x802B6AF8(asm) <-- arch_spin_lock -001 |tcp_v4_rcv(skb = 0x8BD527A0) <-- sk = 0x8BE6B2A0 -002 |ip_local_deliver_finish(skb = 0x8BD527A0) -003 |__netif_receive_skb_core(skb = 0x8BD527A0, ?) -004 |netif_receive_skb(skb = 0x8BD527A0) -005 |elk_poll(napi = 0x8C770500, budget = 64) -006 |net_rx_action(?) -007 |__do_softirq() -008 |do_softirq() -009 |local_bh_enable() -010 |tcp_rcv_established(sk = 0x8BE6B2A0, skb = 0x87D3A9E0, th = 0x814EBE14, ?) -011 |tcp_v4_do_rcv(sk = 0x8BE6B2A0, skb = 0x87D3A9E0) -012 |tcp_delack_timer_handler(sk = 0x8BE6B2A0) -013 |tcp_release_cb(sk = 0x8BE6B2A0) -014 |release_sock(sk = 0x8BE6B2A0) -015 |tcp_sendmsg(?, sk = 0x8BE6B2A0, ?, ?) -016 |sock_sendmsg(sock = 0x8518C4C0, msg = 0x87D8DAA8, size = 4096) -017 |kernel_sendmsg(?, ?, ?, ?, size = 4096) -018 |smb_send_kvec() -019 |smb_send_rqst(server = 0x87C4D400, rqst = 0x87D8DBA0) -020 |cifs_call_async() -021 |cifs_async_writev(wdata = 0x87FD6580) -022 |cifs_writepages(mapping = 0x852096E4, wbc = 0x87D8DC88) -023 |__writeback_single_inode(inode = 0x852095D0, wbc = 0x87D8DC88) -024 |writeback_sb_inodes(sb = 0x87D6D800, wb = 0x87E4A9C0, work = 0x87D8DD88) -025 |__writeback_inodes_wb(wb = 0x87E4A9C0, work = 0x87D8DD88) -026 |wb_writeback(wb = 0x87E4A9C0, work = 0x87D8DD88) -027 |wb_do_writeback(wb = 0x87E4A9C0, force_wait = 0) -028 |bdi_writeback_workfn(work = 0x87E4A9CC) -029 |process_one_work(worker = 0x8B045880, work = 0x87E4A9CC) -030 |worker_thread(__worker = 0x8B045880) -031 |kthread(_create = 0x87CADD90) -032 |ret_from_kernel_thread(asm) Bug occurs because __tcp_checksum_complete_user() enables BH, assuming it is running from softirq context. Lars trace involved a NIC without RX checksum support but other points are problematic as well, like the prequeue stuff. Problem is triggered by a timer, that found socket being owned by user. tcp_release_cb() should call tcp_write_timer_handler() or tcp_delack_timer_handler() in the appropriate context : BH disabled and socket lock held, but 'owned' field cleared, as if they were running from timer handlers. Fixes: 6f458dfb4092 ("tcp: improve latencies of timer triggered events") Reported-by: Lars Persson <lars.persson@axis.com> Tested-by: Lars Persson <lars.persson@axis.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-10 16:50:11 +00:00
/* Warning : release_cb() might need to release sk ownership,
* ie call sock_release_ownership(sk) before us.
*/
tcp: TCP Small Queues This introduce TSQ (TCP Small Queues) TSQ goal is to reduce number of TCP packets in xmit queues (qdisc & device queues), to reduce RTT and cwnd bias, part of the bufferbloat problem. sk->sk_wmem_alloc not allowed to grow above a given limit, allowing no more than ~128KB [1] per tcp socket in qdisc/dev layers at a given time. TSO packets are sized/capped to half the limit, so that we have two TSO packets in flight, allowing better bandwidth use. As a side effect, setting the limit to 40000 automatically reduces the standard gso max limit (65536) to 40000/2 : It can help to reduce latencies of high prio packets, having smaller TSO packets. This means we divert sock_wfree() to a tcp_wfree() handler, to queue/send following frames when skb_orphan() [2] is called for the already queued skbs. Results on my dev machines (tg3/ixgbe nics) are really impressive, using standard pfifo_fast, and with or without TSO/GSO. Without reduction of nominal bandwidth, we have reduction of buffering per bulk sender : < 1ms on Gbit (instead of 50ms with TSO) < 8ms on 100Mbit (instead of 132 ms) I no longer have 4 MBytes backlogged in qdisc by a single netperf session, and both side socket autotuning no longer use 4 Mbytes. As skb destructor cannot restart xmit itself ( as qdisc lock might be taken at this point ), we delegate the work to a tasklet. We use one tasklest per cpu for performance reasons. If tasklet finds a socket owned by the user, it sets TSQ_OWNED flag. This flag is tested in a new protocol method called from release_sock(), to eventually send new segments. [1] New /proc/sys/net/ipv4/tcp_limit_output_bytes tunable [2] skb_orphan() is usually called at TX completion time, but some drivers call it in their start_xmit() handler. These drivers should at least use BQL, or else a single TCP session can still fill the whole NIC TX ring, since TSQ will have no effect. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Dave Taht <dave.taht@bufferbloat.net> Cc: Tom Herbert <therbert@google.com> Cc: Matt Mathis <mattmathis@google.com> Cc: Yuchung Cheng <ycheng@google.com> Cc: Nandita Dukkipati <nanditad@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-07-11 05:50:31 +00:00
if (sk->sk_prot->release_cb)
sk->sk_prot->release_cb(sk);
tcp: tcp_release_cb() should release socket ownership Lars Persson reported following deadlock : -000 |M:0x0:0x802B6AF8(asm) <-- arch_spin_lock -001 |tcp_v4_rcv(skb = 0x8BD527A0) <-- sk = 0x8BE6B2A0 -002 |ip_local_deliver_finish(skb = 0x8BD527A0) -003 |__netif_receive_skb_core(skb = 0x8BD527A0, ?) -004 |netif_receive_skb(skb = 0x8BD527A0) -005 |elk_poll(napi = 0x8C770500, budget = 64) -006 |net_rx_action(?) -007 |__do_softirq() -008 |do_softirq() -009 |local_bh_enable() -010 |tcp_rcv_established(sk = 0x8BE6B2A0, skb = 0x87D3A9E0, th = 0x814EBE14, ?) -011 |tcp_v4_do_rcv(sk = 0x8BE6B2A0, skb = 0x87D3A9E0) -012 |tcp_delack_timer_handler(sk = 0x8BE6B2A0) -013 |tcp_release_cb(sk = 0x8BE6B2A0) -014 |release_sock(sk = 0x8BE6B2A0) -015 |tcp_sendmsg(?, sk = 0x8BE6B2A0, ?, ?) -016 |sock_sendmsg(sock = 0x8518C4C0, msg = 0x87D8DAA8, size = 4096) -017 |kernel_sendmsg(?, ?, ?, ?, size = 4096) -018 |smb_send_kvec() -019 |smb_send_rqst(server = 0x87C4D400, rqst = 0x87D8DBA0) -020 |cifs_call_async() -021 |cifs_async_writev(wdata = 0x87FD6580) -022 |cifs_writepages(mapping = 0x852096E4, wbc = 0x87D8DC88) -023 |__writeback_single_inode(inode = 0x852095D0, wbc = 0x87D8DC88) -024 |writeback_sb_inodes(sb = 0x87D6D800, wb = 0x87E4A9C0, work = 0x87D8DD88) -025 |__writeback_inodes_wb(wb = 0x87E4A9C0, work = 0x87D8DD88) -026 |wb_writeback(wb = 0x87E4A9C0, work = 0x87D8DD88) -027 |wb_do_writeback(wb = 0x87E4A9C0, force_wait = 0) -028 |bdi_writeback_workfn(work = 0x87E4A9CC) -029 |process_one_work(worker = 0x8B045880, work = 0x87E4A9CC) -030 |worker_thread(__worker = 0x8B045880) -031 |kthread(_create = 0x87CADD90) -032 |ret_from_kernel_thread(asm) Bug occurs because __tcp_checksum_complete_user() enables BH, assuming it is running from softirq context. Lars trace involved a NIC without RX checksum support but other points are problematic as well, like the prequeue stuff. Problem is triggered by a timer, that found socket being owned by user. tcp_release_cb() should call tcp_write_timer_handler() or tcp_delack_timer_handler() in the appropriate context : BH disabled and socket lock held, but 'owned' field cleared, as if they were running from timer handlers. Fixes: 6f458dfb4092 ("tcp: improve latencies of timer triggered events") Reported-by: Lars Persson <lars.persson@axis.com> Tested-by: Lars Persson <lars.persson@axis.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-03-10 16:50:11 +00:00
sock_release_ownership(sk);
if (waitqueue_active(&sk->sk_lock.wq))
wake_up(&sk->sk_lock.wq);
spin_unlock_bh(&sk->sk_lock.slock);
}
EXPORT_SYMBOL(release_sock);
/**
* lock_sock_fast - fast version of lock_sock
* @sk: socket
*
* This version should be used for very small section, where process wont block
* return false if fast path is taken:
*
* sk_lock.slock locked, owned = 0, BH disabled
*
* return true if slow path is taken:
*
* sk_lock.slock unlocked, owned = 1, BH enabled
*/
bool lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock)
{
might_sleep();
spin_lock_bh(&sk->sk_lock.slock);
if (!sk->sk_lock.owned)
/*
* Note : We must disable BH
*/
return false;
__lock_sock(sk);
sk->sk_lock.owned = 1;
spin_unlock(&sk->sk_lock.slock);
/*
* The sk_lock has mutex_lock() semantics here:
*/
mutex_acquire(&sk->sk_lock.dep_map, 0, 0, _RET_IP_);
__acquire(&sk->sk_lock.slock);
local_bh_enable();
return true;
}
EXPORT_SYMBOL(lock_sock_fast);
int sock_gettstamp(struct socket *sock, void __user *userstamp,
bool timeval, bool time32)
{
struct sock *sk = sock->sk;
struct timespec64 ts;
sock_enable_timestamp(sk, SOCK_TIMESTAMP);
ts = ktime_to_timespec64(sock_read_timestamp(sk));
if (ts.tv_sec == -1)
return -ENOENT;
if (ts.tv_sec == 0) {
ktime_t kt = ktime_get_real();
sock_write_timestamp(sk, kt);
ts = ktime_to_timespec64(kt);
}
if (timeval)
ts.tv_nsec /= 1000;
#ifdef CONFIG_COMPAT_32BIT_TIME
if (time32)
return put_old_timespec32(&ts, userstamp);
#endif
#ifdef CONFIG_SPARC64
/* beware of padding in sparc64 timeval */
if (timeval && !in_compat_syscall()) {
struct __kernel_old_timeval __user tv = {
.tv_sec = ts.tv_sec,
.tv_usec = ts.tv_nsec,
};
if (copy_to_user(userstamp, &tv, sizeof(tv)))
return -EFAULT;
return 0;
}
#endif
return put_timespec64(&ts, userstamp);
}
EXPORT_SYMBOL(sock_gettstamp);
void sock_enable_timestamp(struct sock *sk, enum sock_flags flag)
{
if (!sock_flag(sk, flag)) {
unsigned long previous_flags = sk->sk_flags;
sock_set_flag(sk, flag);
/*
* we just set one of the two flags which require net
* time stamping, but time stamping might have been on
* already because of the other one
*/
if (sock_needs_netstamp(sk) &&
!(previous_flags & SK_FLAGS_TIMESTAMP))
net_enable_timestamp();
}
}
int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len,
int level, int type)
{
struct sock_exterr_skb *serr;
struct sk_buff *skb;
int copied, err;
err = -EAGAIN;
skb = sock_dequeue_err_skb(sk);
if (skb == NULL)
goto out;
copied = skb->len;
if (copied > len) {
msg->msg_flags |= MSG_TRUNC;
copied = len;
}
err = skb_copy_datagram_msg(skb, 0, msg, copied);
if (err)
goto out_free_skb;
sock_recv_timestamp(msg, sk, skb);
serr = SKB_EXT_ERR(skb);
put_cmsg(msg, level, type, sizeof(serr->ee), &serr->ee);
msg->msg_flags |= MSG_ERRQUEUE;
err = copied;
out_free_skb:
kfree_skb(skb);
out:
return err;
}
EXPORT_SYMBOL(sock_recv_errqueue);
/*
* Get a socket option on an socket.
*
* FIX: POSIX 1003.1g is very ambiguous here. It states that
* asynchronous errors should be reported by getsockopt. We assume
* this means if you specify SO_ERROR (otherwise whats the point of it).
*/
int sock_common_getsockopt(struct socket *sock, int level, int optname,
char __user *optval, int __user *optlen)
{
struct sock *sk = sock->sk;
return sk->sk_prot->getsockopt(sk, level, optname, optval, optlen);
}
EXPORT_SYMBOL(sock_common_getsockopt);
int sock_common_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
int flags)
{
struct sock *sk = sock->sk;
int addr_len = 0;
int err;
err = sk->sk_prot->recvmsg(sk, msg, size, flags & MSG_DONTWAIT,
flags & ~MSG_DONTWAIT, &addr_len);
if (err >= 0)
msg->msg_namelen = addr_len;
return err;
}
EXPORT_SYMBOL(sock_common_recvmsg);
/*
* Set socket options on an inet socket.
*/
int sock_common_setsockopt(struct socket *sock, int level, int optname,
sockptr_t optval, unsigned int optlen)
{
struct sock *sk = sock->sk;
return sk->sk_prot->setsockopt(sk, level, optname, optval, optlen);
}
EXPORT_SYMBOL(sock_common_setsockopt);
void sk_common_release(struct sock *sk)
{
if (sk->sk_prot->destroy)
sk->sk_prot->destroy(sk);
/*
* Observation: when sk_common_release is called, processes have
* no access to socket. But net still has.
* Step one, detach it from networking:
*
* A. Remove from hash tables.
*/
sk->sk_prot->unhash(sk);
/*
* In this point socket cannot receive new packets, but it is possible
* that some packets are in flight because some CPU runs receiver and
* did hash table lookup before we unhashed socket. They will achieve
* receive queue and will be purged by socket destructor.
*
* Also we still have packets pending on receive queue and probably,
* our own packets waiting in device queues. sock_destroy will drain
* receive queue, but transmitted packets will delay socket destruction
* until the last reference will be released.
*/
sock_orphan(sk);
xfrm_sk_free_policy(sk);
sk_refcnt_debug_release(sk);
net: use a per task frag allocator We currently use a per socket order-0 page cache for tcp_sendmsg() operations. This page is used to build fragments for skbs. Its done to increase probability of coalescing small write() into single segments in skbs still in write queue (not yet sent) But it wastes a lot of memory for applications handling many mostly idle sockets, since each socket holds one page in sk->sk_sndmsg_page Its also quite inefficient to build TSO 64KB packets, because we need about 16 pages per skb on arches where PAGE_SIZE = 4096, so we hit page allocator more than wanted. This patch adds a per task frag allocator and uses bigger pages, if available. An automatic fallback is done in case of memory pressure. (up to 32768 bytes per frag, thats order-3 pages on x86) This increases TCP stream performance by 20% on loopback device, but also benefits on other network devices, since 8x less frags are mapped on transmit and unmapped on tx completion. Alexander Duyck mentioned a probable performance win on systems with IOMMU enabled. Its possible some SG enabled hardware cant cope with bigger fragments, but their ndo_start_xmit() should already handle this, splitting a fragment in sub fragments, since some arches have PAGE_SIZE=65536 Successfully tested on various ethernet devices. (ixgbe, igb, bnx2x, tg3, mellanox mlx4) Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Ben Hutchings <bhutchings@solarflare.com> Cc: Vijay Subramanian <subramanian.vijay@gmail.com> Cc: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Vijay Subramanian <subramanian.vijay@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-23 23:04:42 +00:00
sock_put(sk);
}
EXPORT_SYMBOL(sk_common_release);
void sk_get_meminfo(const struct sock *sk, u32 *mem)
{
memset(mem, 0, sizeof(*mem) * SK_MEMINFO_VARS);
mem[SK_MEMINFO_RMEM_ALLOC] = sk_rmem_alloc_get(sk);
mem[SK_MEMINFO_RCVBUF] = READ_ONCE(sk->sk_rcvbuf);
mem[SK_MEMINFO_WMEM_ALLOC] = sk_wmem_alloc_get(sk);
mem[SK_MEMINFO_SNDBUF] = READ_ONCE(sk->sk_sndbuf);
mem[SK_MEMINFO_FWD_ALLOC] = sk->sk_forward_alloc;
mem[SK_MEMINFO_WMEM_QUEUED] = READ_ONCE(sk->sk_wmem_queued);
mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc);
net: silence KCSAN warnings about sk->sk_backlog.len reads sk->sk_backlog.len can be written by BH handlers, and read from process contexts in a lockless way. Note the write side should also use WRITE_ONCE() or a variant. We need some agreement about the best way to do this. syzbot reported : BUG: KCSAN: data-race in tcp_add_backlog / tcp_grow_window.isra.0 write to 0xffff88812665f32c of 4 bytes by interrupt on cpu 1: sk_add_backlog include/net/sock.h:934 [inline] tcp_add_backlog+0x4a0/0xcc0 net/ipv4/tcp_ipv4.c:1737 tcp_v4_rcv+0x1aba/0x1bf0 net/ipv4/tcp_ipv4.c:1925 ip_protocol_deliver_rcu+0x51/0x470 net/ipv4/ip_input.c:204 ip_local_deliver_finish+0x110/0x140 net/ipv4/ip_input.c:231 NF_HOOK include/linux/netfilter.h:305 [inline] NF_HOOK include/linux/netfilter.h:299 [inline] ip_local_deliver+0x133/0x210 net/ipv4/ip_input.c:252 dst_input include/net/dst.h:442 [inline] ip_rcv_finish+0x121/0x160 net/ipv4/ip_input.c:413 NF_HOOK include/linux/netfilter.h:305 [inline] NF_HOOK include/linux/netfilter.h:299 [inline] ip_rcv+0x18f/0x1a0 net/ipv4/ip_input.c:523 __netif_receive_skb_one_core+0xa7/0xe0 net/core/dev.c:5004 __netif_receive_skb+0x37/0xf0 net/core/dev.c:5118 netif_receive_skb_internal+0x59/0x190 net/core/dev.c:5208 napi_skb_finish net/core/dev.c:5671 [inline] napi_gro_receive+0x28f/0x330 net/core/dev.c:5704 receive_buf+0x284/0x30b0 drivers/net/virtio_net.c:1061 virtnet_receive drivers/net/virtio_net.c:1323 [inline] virtnet_poll+0x436/0x7d0 drivers/net/virtio_net.c:1428 napi_poll net/core/dev.c:6352 [inline] net_rx_action+0x3ae/0xa50 net/core/dev.c:6418 read to 0xffff88812665f32c of 4 bytes by task 7292 on cpu 0: tcp_space include/net/tcp.h:1373 [inline] tcp_grow_window.isra.0+0x6b/0x480 net/ipv4/tcp_input.c:413 tcp_event_data_recv+0x68f/0x990 net/ipv4/tcp_input.c:717 tcp_rcv_established+0xbfe/0xf50 net/ipv4/tcp_input.c:5618 tcp_v4_do_rcv+0x381/0x4e0 net/ipv4/tcp_ipv4.c:1542 sk_backlog_rcv include/net/sock.h:945 [inline] __release_sock+0x135/0x1e0 net/core/sock.c:2427 release_sock+0x61/0x160 net/core/sock.c:2943 tcp_recvmsg+0x63b/0x1a30 net/ipv4/tcp.c:2181 inet_recvmsg+0xbb/0x250 net/ipv4/af_inet.c:838 sock_recvmsg_nosec net/socket.c:871 [inline] sock_recvmsg net/socket.c:889 [inline] sock_recvmsg+0x92/0xb0 net/socket.c:885 sock_read_iter+0x15f/0x1e0 net/socket.c:967 call_read_iter include/linux/fs.h:1864 [inline] new_sync_read+0x389/0x4f0 fs/read_write.c:414 __vfs_read+0xb1/0xc0 fs/read_write.c:427 vfs_read fs/read_write.c:461 [inline] vfs_read+0x143/0x2c0 fs/read_write.c:446 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 7292 Comm: syz-fuzzer Not tainted 5.3.0+ #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
2019-10-09 22:41:03 +00:00
mem[SK_MEMINFO_BACKLOG] = READ_ONCE(sk->sk_backlog.len);
mem[SK_MEMINFO_DROPS] = atomic_read(&sk->sk_drops);
}
#ifdef CONFIG_PROC_FS
#define PROTO_INUSE_NR 64 /* should be enough for the first time */
struct prot_inuse {
int val[PROTO_INUSE_NR];
};
static DECLARE_BITMAP(proto_inuse_idx, PROTO_INUSE_NR);
void sock_prot_inuse_add(struct net *net, struct proto *prot, int val)
{
__this_cpu_add(net->core.prot_inuse->val[prot->inuse_idx], val);
}
EXPORT_SYMBOL_GPL(sock_prot_inuse_add);
int sock_prot_inuse_get(struct net *net, struct proto *prot)
{
int cpu, idx = prot->inuse_idx;
int res = 0;
for_each_possible_cpu(cpu)
res += per_cpu_ptr(net->core.prot_inuse, cpu)->val[idx];
return res >= 0 ? res : 0;
}
EXPORT_SYMBOL_GPL(sock_prot_inuse_get);
static void sock_inuse_add(struct net *net, int val)
{
this_cpu_add(*net->core.sock_inuse, val);
}
int sock_inuse_get(struct net *net)
{
int cpu, res = 0;
for_each_possible_cpu(cpu)
res += *per_cpu_ptr(net->core.sock_inuse, cpu);
return res;
}
EXPORT_SYMBOL_GPL(sock_inuse_get);
static int __net_init sock_inuse_init_net(struct net *net)
{
net->core.prot_inuse = alloc_percpu(struct prot_inuse);
if (net->core.prot_inuse == NULL)
return -ENOMEM;
net->core.sock_inuse = alloc_percpu(int);
if (net->core.sock_inuse == NULL)
goto out;
return 0;
out:
free_percpu(net->core.prot_inuse);
return -ENOMEM;
}
static void __net_exit sock_inuse_exit_net(struct net *net)
{
free_percpu(net->core.prot_inuse);
free_percpu(net->core.sock_inuse);
}
static struct pernet_operations net_inuse_ops = {
.init = sock_inuse_init_net,
.exit = sock_inuse_exit_net,
};
static __init int net_inuse_init(void)
{
if (register_pernet_subsys(&net_inuse_ops))
panic("Cannot initialize net inuse counters");
return 0;
}
core_initcall(net_inuse_init);
static int assign_proto_idx(struct proto *prot)
{
prot->inuse_idx = find_first_zero_bit(proto_inuse_idx, PROTO_INUSE_NR);
if (unlikely(prot->inuse_idx == PROTO_INUSE_NR - 1)) {
pr_err("PROTO_INUSE_NR exhausted\n");
return -ENOSPC;
}
set_bit(prot->inuse_idx, proto_inuse_idx);
return 0;
}
static void release_proto_idx(struct proto *prot)
{
if (prot->inuse_idx != PROTO_INUSE_NR - 1)
clear_bit(prot->inuse_idx, proto_inuse_idx);
}
#else
static inline int assign_proto_idx(struct proto *prot)
{
return 0;
}
static inline void release_proto_idx(struct proto *prot)
{
}
static void sock_inuse_add(struct net *net, int val)
{
}
#endif
static void tw_prot_cleanup(struct timewait_sock_ops *twsk_prot)
{
if (!twsk_prot)
return;
kfree(twsk_prot->twsk_slab_name);
twsk_prot->twsk_slab_name = NULL;
kmem_cache_destroy(twsk_prot->twsk_slab);
twsk_prot->twsk_slab = NULL;
}
static void req_prot_cleanup(struct request_sock_ops *rsk_prot)
{
if (!rsk_prot)
return;
kfree(rsk_prot->slab_name);
rsk_prot->slab_name = NULL;
kmem_cache_destroy(rsk_prot->slab);
rsk_prot->slab = NULL;
}
static int req_prot_init(const struct proto *prot)
{
struct request_sock_ops *rsk_prot = prot->rsk_prot;
if (!rsk_prot)
return 0;
rsk_prot->slab_name = kasprintf(GFP_KERNEL, "request_sock_%s",
prot->name);
if (!rsk_prot->slab_name)
return -ENOMEM;
rsk_prot->slab = kmem_cache_create(rsk_prot->slab_name,
rsk_prot->obj_size, 0,
SLAB_ACCOUNT | prot->slab_flags,
NULL);
if (!rsk_prot->slab) {
pr_crit("%s: Can't create request sock SLAB cache!\n",
prot->name);
return -ENOMEM;
}
return 0;
}
int proto_register(struct proto *prot, int alloc_slab)
{
int ret = -ENOBUFS;
if (alloc_slab) {
prot->slab = kmem_cache_create_usercopy(prot->name,
prot->obj_size, 0,
SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT |
prot->slab_flags,
net: Restrict unwhitelisted proto caches to size 0 Now that protocols have been annotated (the copy of icsk_ca_ops->name is of an ops field from outside the slab cache): $ git grep 'copy_.*_user.*sk.*->' caif/caif_socket.c: copy_from_user(&cf_sk->conn_req.param.data, ov, ol)) { ipv4/raw.c: if (copy_from_user(&raw_sk(sk)->filter, optval, optlen)) ipv4/raw.c: copy_to_user(optval, &raw_sk(sk)->filter, len)) ipv4/tcp.c: if (copy_to_user(optval, icsk->icsk_ca_ops->name, len)) ipv4/tcp.c: if (copy_to_user(optval, icsk->icsk_ulp_ops->name, len)) ipv6/raw.c: if (copy_from_user(&raw6_sk(sk)->filter, optval, optlen)) ipv6/raw.c: if (copy_to_user(optval, &raw6_sk(sk)->filter, len)) sctp/socket.c: if (copy_from_user(&sctp_sk(sk)->subscribe, optval, optlen)) sctp/socket.c: if (copy_to_user(optval, &sctp_sk(sk)->subscribe, len)) sctp/socket.c: if (copy_to_user(optval, &sctp_sk(sk)->initmsg, len)) we can switch the default proto usercopy region to size 0. Any protocols needing to add whitelisted regions must annotate the fields with the useroffset and usersize fields of struct proto. This patch is modified from Brad Spengler/PaX Team's PAX_USERCOPY whitelisting code in the last public patch of grsecurity/PaX based on my understanding of the code. Changes or omissions from the original code are mine and don't reflect the original grsecurity/PaX code. Cc: "David S. Miller" <davem@davemloft.net> Cc: Eric Dumazet <edumazet@google.com> Cc: Paolo Abeni <pabeni@redhat.com> Cc: David Howells <dhowells@redhat.com> Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook <keescook@chromium.org>
2017-08-24 23:59:38 +00:00
prot->useroffset, prot->usersize,
udp: RCU handling for Unicast packets. Goals are : 1) Optimizing handling of incoming Unicast UDP frames, so that no memory writes should happen in the fast path. Note: Multicasts and broadcasts still will need to take a lock, because doing a full lockless lookup in this case is difficult. 2) No expensive operations in the socket bind/unhash phases : - No expensive synchronize_rcu() calls. - No added rcu_head in socket structure, increasing memory needs, but more important, forcing us to use call_rcu() calls, that have the bad property of making sockets structure cold. (rcu grace period between socket freeing and its potential reuse make this socket being cold in CPU cache). David did a previous patch using call_rcu() and noticed a 20% impact on TCP connection rates. Quoting Cristopher Lameter : "Right. That results in cacheline cooldown. You'd want to recycle the object as they are cache hot on a per cpu basis. That is screwed up by the delayed regular rcu processing. We have seen multiple regressions due to cacheline cooldown. The only choice in cacheline hot sensitive areas is to deal with the complexity that comes with SLAB_DESTROY_BY_RCU or give up on RCU." - Because udp sockets are allocated from dedicated kmem_cache, use of SLAB_DESTROY_BY_RCU can help here. Theory of operation : --------------------- As the lookup is lockfree (using rcu_read_lock()/rcu_read_unlock()), special attention must be taken by readers and writers. Use of SLAB_DESTROY_BY_RCU is tricky too, because a socket can be freed, reused, inserted in a different chain or in worst case in the same chain while readers could do lookups in the same time. In order to avoid loops, a reader must check each socket found in a chain really belongs to the chain the reader was traversing. If it finds a mismatch, lookup must start again at the begining. This *restart* loop is the reason we had to use rdlock for the multicast case, because we dont want to send same message several times to the same socket. We use RCU only for fast path. Thus, /proc/net/udp still takes spinlocks. Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-10-29 09:11:14 +00:00
NULL);
if (prot->slab == NULL) {
pr_crit("%s: Can't create sock SLAB cache!\n",
prot->name);
goto out;
}
if (req_prot_init(prot))
goto out_free_request_sock_slab;
if (prot->twsk_prot != NULL) {
prot->twsk_prot->twsk_slab_name = kasprintf(GFP_KERNEL, "tw_sock_%s", prot->name);
if (prot->twsk_prot->twsk_slab_name == NULL)
goto out_free_request_sock_slab;
prot->twsk_prot->twsk_slab =
kmem_cache_create(prot->twsk_prot->twsk_slab_name,
prot->twsk_prot->twsk_obj_size,
0,
SLAB_ACCOUNT |
prot->slab_flags,
NULL);
if (prot->twsk_prot->twsk_slab == NULL)
goto out_free_timewait_sock_slab;
}
}
mutex_lock(&proto_list_mutex);
ret = assign_proto_idx(prot);
if (ret) {
mutex_unlock(&proto_list_mutex);
goto out_free_timewait_sock_slab;
}
list_add(&prot->node, &proto_list);
mutex_unlock(&proto_list_mutex);
return ret;
out_free_timewait_sock_slab:
if (alloc_slab && prot->twsk_prot)
tw_prot_cleanup(prot->twsk_prot);
out_free_request_sock_slab:
if (alloc_slab) {
req_prot_cleanup(prot->rsk_prot);
kmem_cache_destroy(prot->slab);
prot->slab = NULL;
}
out:
return ret;
}
EXPORT_SYMBOL(proto_register);
void proto_unregister(struct proto *prot)
{
mutex_lock(&proto_list_mutex);
release_proto_idx(prot);
list_del(&prot->node);
mutex_unlock(&proto_list_mutex);
kmem_cache_destroy(prot->slab);
prot->slab = NULL;
req_prot_cleanup(prot->rsk_prot);
tw_prot_cleanup(prot->twsk_prot);
}
EXPORT_SYMBOL(proto_unregister);
sock_diag: request _diag module only when the family or proto has been registered Now when using 'ss' in iproute, kernel would try to load all _diag modules, which also causes corresponding family and proto modules to be loaded as well due to module dependencies. Like after running 'ss', sctp, dccp, af_packet (if it works as a module) would be loaded. For example: $ lsmod|grep sctp $ ss $ lsmod|grep sctp sctp_diag 16384 0 sctp 323584 5 sctp_diag inet_diag 24576 4 raw_diag,tcp_diag,sctp_diag,udp_diag libcrc32c 16384 3 nf_conntrack,nf_nat,sctp As these family and proto modules are loaded unintentionally, it could cause some problems, like: - Some debug tools use 'ss' to collect the socket info, which loads all those diag and family and protocol modules. It's noisy for identifying issues. - Users usually expect to drop sctp init packet silently when they have no sense of sctp protocol instead of sending abort back. - It wastes resources (especially with multiple netns), and SCTP module can't be unloaded once it's loaded. ... In short, it's really inappropriate to have these family and proto modules loaded unexpectedly when just doing debugging with inet_diag. This patch is to introduce sock_load_diag_module() where it loads the _diag module only when it's corresponding family or proto has been already registered. Note that we can't just load _diag module without the family or proto loaded, as some symbols used in _diag module are from the family or proto module. v1->v2: - move inet proto check to inet_diag to avoid a compiling err. v2->v3: - define sock_load_diag_module in sock.c and export one symbol only. - improve the changelog. Reported-by: Sabrina Dubroca <sd@queasysnail.net> Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Acked-by: Phil Sutter <phil@nwl.cc> Acked-by: Sabrina Dubroca <sd@queasysnail.net> Signed-off-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-03-10 10:57:50 +00:00
int sock_load_diag_module(int family, int protocol)
{
if (!protocol) {
if (!sock_is_registered(family))
return -ENOENT;
return request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK,
NETLINK_SOCK_DIAG, family);
}
#ifdef CONFIG_INET
if (family == AF_INET &&
protocol != IPPROTO_RAW &&
protocol < MAX_INET_PROTOS &&
sock_diag: request _diag module only when the family or proto has been registered Now when using 'ss' in iproute, kernel would try to load all _diag modules, which also causes corresponding family and proto modules to be loaded as well due to module dependencies. Like after running 'ss', sctp, dccp, af_packet (if it works as a module) would be loaded. For example: $ lsmod|grep sctp $ ss $ lsmod|grep sctp sctp_diag 16384 0 sctp 323584 5 sctp_diag inet_diag 24576 4 raw_diag,tcp_diag,sctp_diag,udp_diag libcrc32c 16384 3 nf_conntrack,nf_nat,sctp As these family and proto modules are loaded unintentionally, it could cause some problems, like: - Some debug tools use 'ss' to collect the socket info, which loads all those diag and family and protocol modules. It's noisy for identifying issues. - Users usually expect to drop sctp init packet silently when they have no sense of sctp protocol instead of sending abort back. - It wastes resources (especially with multiple netns), and SCTP module can't be unloaded once it's loaded. ... In short, it's really inappropriate to have these family and proto modules loaded unexpectedly when just doing debugging with inet_diag. This patch is to introduce sock_load_diag_module() where it loads the _diag module only when it's corresponding family or proto has been already registered. Note that we can't just load _diag module without the family or proto loaded, as some symbols used in _diag module are from the family or proto module. v1->v2: - move inet proto check to inet_diag to avoid a compiling err. v2->v3: - define sock_load_diag_module in sock.c and export one symbol only. - improve the changelog. Reported-by: Sabrina Dubroca <sd@queasysnail.net> Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Acked-by: Phil Sutter <phil@nwl.cc> Acked-by: Sabrina Dubroca <sd@queasysnail.net> Signed-off-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-03-10 10:57:50 +00:00
!rcu_access_pointer(inet_protos[protocol]))
return -ENOENT;
#endif
return request_module("net-pf-%d-proto-%d-type-%d-%d", PF_NETLINK,
NETLINK_SOCK_DIAG, family, protocol);
}
EXPORT_SYMBOL(sock_load_diag_module);
#ifdef CONFIG_PROC_FS
static void *proto_seq_start(struct seq_file *seq, loff_t *pos)
__acquires(proto_list_mutex)
{
mutex_lock(&proto_list_mutex);
return seq_list_start_head(&proto_list, *pos);
}
static void *proto_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
return seq_list_next(v, &proto_list, pos);
}
static void proto_seq_stop(struct seq_file *seq, void *v)
__releases(proto_list_mutex)
{
mutex_unlock(&proto_list_mutex);
}
static char proto_method_implemented(const void *method)
{
return method == NULL ? 'n' : 'y';
}
static long sock_prot_memory_allocated(struct proto *proto)
{
return proto->memory_allocated != NULL ? proto_memory_allocated(proto) : -1L;
}
static const char *sock_prot_memory_pressure(struct proto *proto)
{
return proto->memory_pressure != NULL ?
proto_memory_pressure(proto) ? "yes" : "no" : "NI";
}
static void proto_seq_printf(struct seq_file *seq, struct proto *proto)
{
seq_printf(seq, "%-9s %4u %6d %6ld %-3s %6u %-3s %-10s "
"%2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c\n",
proto->name,
proto->obj_size,
sock_prot_inuse_get(seq_file_net(seq), proto),
sock_prot_memory_allocated(proto),
sock_prot_memory_pressure(proto),
proto->max_header,
proto->slab == NULL ? "no" : "yes",
module_name(proto->owner),
proto_method_implemented(proto->close),
proto_method_implemented(proto->connect),
proto_method_implemented(proto->disconnect),
proto_method_implemented(proto->accept),
proto_method_implemented(proto->ioctl),
proto_method_implemented(proto->init),
proto_method_implemented(proto->destroy),
proto_method_implemented(proto->shutdown),
proto_method_implemented(proto->setsockopt),
proto_method_implemented(proto->getsockopt),
proto_method_implemented(proto->sendmsg),
proto_method_implemented(proto->recvmsg),
proto_method_implemented(proto->sendpage),
proto_method_implemented(proto->bind),
proto_method_implemented(proto->backlog_rcv),
proto_method_implemented(proto->hash),
proto_method_implemented(proto->unhash),
proto_method_implemented(proto->get_port),
proto_method_implemented(proto->enter_memory_pressure));
}
static int proto_seq_show(struct seq_file *seq, void *v)
{
if (v == &proto_list)
seq_printf(seq, "%-9s %-4s %-8s %-6s %-5s %-7s %-4s %-10s %s",
"protocol",
"size",
"sockets",
"memory",
"press",
"maxhdr",
"slab",
"module",
"cl co di ac io in de sh ss gs se re sp bi br ha uh gp em\n");
else
proto_seq_printf(seq, list_entry(v, struct proto, node));
return 0;
}
static const struct seq_operations proto_seq_ops = {
.start = proto_seq_start,
.next = proto_seq_next,
.stop = proto_seq_stop,
.show = proto_seq_show,
};
static __net_init int proto_init_net(struct net *net)
{
if (!proc_create_net("protocols", 0444, net->proc_net, &proto_seq_ops,
sizeof(struct seq_net_private)))
return -ENOMEM;
return 0;
}
static __net_exit void proto_exit_net(struct net *net)
{
remove_proc_entry("protocols", net->proc_net);
}
static __net_initdata struct pernet_operations proto_net_ops = {
.init = proto_init_net,
.exit = proto_exit_net,
};
static int __init proto_init(void)
{
return register_pernet_subsys(&proto_net_ops);
}
subsys_initcall(proto_init);
#endif /* PROC_FS */
#ifdef CONFIG_NET_RX_BUSY_POLL
bool sk_busy_loop_end(void *p, unsigned long start_time)
{
struct sock *sk = p;
return !skb_queue_empty_lockless(&sk->sk_receive_queue) ||
sk_busy_loop_timeout(sk, start_time);
}
EXPORT_SYMBOL(sk_busy_loop_end);
#endif /* CONFIG_NET_RX_BUSY_POLL */
int sock_bind_add(struct sock *sk, struct sockaddr *addr, int addr_len)
{
if (!sk->sk_prot->bind_add)
return -EOPNOTSUPP;
return sk->sk_prot->bind_add(sk, addr, addr_len);
}
EXPORT_SYMBOL(sock_bind_add);